© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Apollo Research · Taylor · Identifying Functionally Important Features with End-to-End Sparse Dictionary Learning
    5. GPT2-Small
    7. Residual Similar CE E2E Recon
    9. 6-RES_SCEFR-AJT
    11. 6222
    Prev
    Next
    INDEX
    Explanations

    terms related to computer systems, including supercomputers, deep learning, and technical capabilities

    oai_token-act-pair · gpt-3.5-turbo

    words or parts of words containing the sequence "com"

    oai_token-act-pair · gpt-3.5-turboTriggered by @danbraun
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    neuronpedia/gpt2-small__res_scefr-ajt/6-res_scefr-ajt
    Prompts (Dashboard)
    12,288 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    46,080
    Data Type
    torch.float32
    Hook Point
    blocks.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    apollo-research/Skylion007-openwebtext-tokenizer-gpt2
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    706
    +0.11
    0.5%
    746
    +0.11
    0.5%
    115
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    706
    +0.11
    0.05
    115
    +0.11
    0.04
    231
    +0.11
    0.03
    Negative Logits
     AFL
    -0.66
     Tackle
    -0.62
    href
    -0.61
     Tribune
    -0.59
     thirds
    -0.59
     Barcl
    -0.58
    REDACTED
    -0.58
     Citation
    -0.57
     contagious
    -0.56
    EStreamFrame
    -0.56
    POSITIVE LOGITS
    pleted
    1.13
    fortable
    1.12
    puters
    1.04
    puting
    0.94
    hester
    0.90
    pleting
    0.86
    secut
    0.86
    nan
    0.85
    fman
    0.83
    bing
    0.83
    Activations Density 0.504%

    No Known Activations