© 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 Local
    9. 6-RES_SCL-AJT
    11. 36234
    Prev
    Next
    INDEX
    Explanations

    content related to educational materials focused on specific topics, activities, and resources

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    neuronpedia/gpt2-small__res_scl-ajt/6-res_scl-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
    566
    +0.06
    0.6%
    549
    +0.05
    0.5%
    308
    +0.05
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    326
    +0.06
    0.21
    288
    +0.05
    0.22
    57
    +0.05
    0.07
    Negative Logits
    eret
    -0.34
    osta
    -0.34
    eworthy
    -0.33
    water
    -0.32
    ga
    -0.31
    ulet
    -0.31
    lia
    -0.31
    urnal
    -0.30
    abad
    -0.30
    ldom
    -0.30
    POSITIVE LOGITS
    ISM
    0.52
    TERN
    0.47
    MAN
    0.47
    ISTER
    0.46
    FORM
    0.46
    ICS
    0.46
    MENTS
    0.45
    ANC
    0.45
    IONS
    0.45
    ARY
    0.45
    Activations Density 6.682%

    No Known Activations