© 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. 37215
    Prev
    Next
    INDEX
    Explanations

    special characters and numerical values enclosed in "< >" characters

    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
    +0.15
    0.7%
    288
    +0.11
    0.5%
    19
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    302
    +0.15
    0.11
    326
    +0.11
    0.17
    415
    +0.11
    0.07
    Negative Logits
    xual
    -0.98
    itude
    -0.78
    rison
    -0.77
    lier
    -0.74
    staking
    -0.71
    instein
    -0.71
     Flavoring
    -0.71
    sighted
    -0.71
    xon
    -0.70
    lies
    -0.68
    POSITIVE LOGITS
    dfx
    1.32
    427
    0.81
    ovember
    0.81
    329
    0.80
    arious
    0.80
    00
    0.78
    ULT
    0.77
     cents
    0.77
    328
    0.76
     Minutes
    0.76
    Activations Density 5.028%

    No Known Activations