© 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. 6635
    Prev
    Next
    INDEX
    Explanations

    references to artists, photographers, or individuals involved in creating visual works of art or capturing visual content

    oai_token-act-pair · gpt-3.5-turbo
    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
    167
    +0.16
    0.6%
    575
    +0.13
    0.5%
    154
    +0.13
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    575
    +0.16
    0.14
    288
    +0.13
    0.14
    537
    +0.13
    0.10
    Negative Logits
     Pradesh
    -0.96
     Territories
    -0.85
    ories
    -0.77
     Leafs
    -0.77
    croft
    -0.74
     Bulls
    -0.74
     UP
    -0.74
    plings
    -0.72
     Matter
    -0.70
    ceed
    -0.70
    POSITIVE LOGITS
     extraord
    1.23
    esses
    1.14
    ess
    1.12
     laureate
    1.11
    sonian
    1.04
     beware
    1.01
     specializing
    0.98
    paces
    0.98
    pocket
    0.98
     who
    0.97
    Activations Density 1.723%

    No Known Activations