© 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 EvalsExportsinterp-engineNEWAPI 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. 2051
    Prev
    Next
    INDEX
    Explanations

    scientific and technical terms related to research methodology and academic publications

    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
    719
    +0.11
    0.4%
    447
    +0.11
    0.4%
    355
    +0.11
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    498
    +0.11
    0.03
    555
    +0.11
    0.02
    668
    +0.11
    0.02
    Negative Logits
    cit
    -0.89
    hm
    -0.86
    iscopal
    -0.85
    igans
    -0.82
    quickShipAvailable
    -0.82
     horm
    -0.81
    aepernick
    -0.81
    warm
    -0.81
    sov
    -0.80
    hak
    -0.78
    POSITIVE LOGITS
     Procedures
    0.96
     procedures
    0.82
     Dir
    0.77
     Instrument
    0.75
     languages
    0.75
     Disaster
    0.74
     Streets
    0.74
     procedure
    0.72
    ²¾
    0.71
     advance
    0.70
    Activations Density 0.336%

    No Known Activations