© 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. 32019
    Prev
    Next
    INDEX
    Explanations

    portions of text within square brackets

    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
    151
    +0.12
    0.6%
    6
    +0.11
    0.5%
    447
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    263
    +0.12
    0.10
    6
    +0.11
    0.14
    316
    +0.10
    0.09
    Negative Logits
    jah
    -0.77
     downs
    -0.75
    isen
    -0.68
    ework
    -0.67
    pen
    -0.67
    imates
    -0.65
    wn
    -0.64
    ilion
    -0.63
    wan
    -0.62
     effic
    -0.62
    POSITIVE LOGITS
    SHIP
    0.78
     Anyway
    0.76
    ({
    0.74
    */
    0.74
    >]
    0.73
     =================================
    0.71
    [/
    0.70
     Likewise
    0.70
    <|endoftext|>
    0.69
    ↵↵
    0.69
    Activations Density 7.480%

    No Known Activations