© 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. 36946
    Prev
    Next
    INDEX
    Explanations

    names and terms related to law, legal proceedings, and political figures

    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
    +0.20
    0.8%
    670
    +0.16
    0.6%
    566
    +0.14
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    699
    +0.20
    0.02
    288
    +0.16
    0.17
    235
    +0.14
    0.09
    Negative Logits
    soDeliveryDate
    -0.97
    nl
    -0.93
    rontal
    -0.91
    ingen
    -0.89
    olicy
    -0.83
     Beir
    -0.82
    staff
    -0.81
    ulates
    -0.81
    nesses
    -0.78
    pread
    -0.77
    POSITIVE LOGITS
    xit
    1.18
    cki
    1.11
    ttes
    1.01
    uca
    1.00
    ague
    0.96
    jandro
    0.95
    ea
    0.94
    ppo
    0.94
    ei
    0.94
    lla
    0.93
    Activations Density 6.302%

    No Known Activations