© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 45705
    Prev
    Next
    INDEX
    Explanations

    numerical values separated by '–'

    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
    Neuron Alignment
    Index
    Value
    % of L₁
    447
    +0.29
    1.3%
    640
    +0.14
    0.6%
    537
    +0.13
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    640
    +0.29
    0.22
    517
    +0.14
    0.11
    393
    +0.13
    0.23
    Negative Logits
    ãĥ¥
    -0.88
     fut
    -0.68
     shorth
    -0.67
     answ
    -0.67
    buck
    -0.65
    sing
    -0.65
     artif
    -0.65
     commer
    -0.64
     footing
    -0.63
    matical
    -0.62
    POSITIVE LOGITS
    âķ
    0.83
     srfAttach
    0.77
     //[
    0.75
     =>
    0.74
    >]
    0.71
     Parables
    0.70
    *.
    0.70
    ^{
    0.68
     Committees
    0.66
    ONSORED
    0.66
    Activations Density 11.067%

    No Known Activations