© 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 E2E Recon
    9. 6-RES_SCEFR-AJT
    11. 8889
    Prev
    Next
    INDEX
    Explanations

    phrases related to international politics and negotiations

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    neuronpedia/gpt2-small__res_scefr-ajt/6-res_scefr-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
    393
    +0.29
    1.6%
    669
    +0.11
    0.6%
    608
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    669
    +0.29
    0.13
    608
    +0.11
    0.15
    393
    +0.10
    0.15
    Negative Logits
    igue
    -0.59
    itent
    -0.58
    nets
    -0.55
     reperto
    -0.55
    owner
    -0.55
    acus
    -0.55
    soType
    -0.53
    aire
    -0.53
    chool
    -0.53
    ilver
    -0.52
    POSITIVE LOGITS
     sorts
    0.91
     course
    0.76
     varying
    0.69
     those
    0.69
     these
    0.68
     both
    0.66
     the
    0.64
     what
    0.64
     either
    0.63
     them
    0.60
    Activations Density 2.731%

    No Known Activations