© 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. 36881
    Prev
    Next
    INDEX
    Explanations

    statistical information from research papers related to social and environmental effects of various factors

    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
    447
    +0.27
    1.6%
    413
    +0.08
    0.5%
    244
    +0.08
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    344
    +0.27
    0.17
    608
    +0.08
    0.22
    195
    +0.08
    -0.03
    Negative Logits
    soever
    -0.58
    gee
    -0.53
     yours
    -0.52
    Reviewed
    -0.50
     forever
    -0.50
     mates
    -0.48
     wisely
    -0.47
    !/
    -0.47
     entails
    -0.47
    wered
    -0.47
    POSITIVE LOGITS
     similarities
    0.80
     overlap
    0.71
     similarity
    0.70
     discrepancies
    0.70
     inconsistency
    0.70
     improvement
    0.69
     discrepancy
    0.68
     correlation
    0.67
     uptick
    0.66
     deterioration
    0.63
    Activations Density 18.569%

    No Known Activations