© 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. 31115
    Prev
    Next
    INDEX
    Explanations

    references to existing infrastructure

    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
    +0.31
    1.4%
    481
    +0.13
    0.6%
    423
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    362
    +0.31
    0.15
    393
    +0.13
    0.24
    640
    +0.11
    0.21
    Negative Logits
    ousse
    -0.93
    alion
    -0.83
    ÃŃa
    -0.78
    owitz
    -0.76
    aminer
    -0.74
    ertodd
    -0.73
    rea
    -0.73
    ueller
    -0.73
    oche
    -0.72
    olic
    -0.72
    POSITIVE LOGITS
     existing
    0.77
    existing
    0.74
     arrangements
    0.72
     liabilities
    0.71
     generations
    0.70
     precedent
    0.69
     tenant
    0.69
     testament
    0.68
    foundland
    0.67
     contiguous
    0.66
    Activations Density 10.949%

    No Known Activations