© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 7771
    Prev
    Next
    INDEX
    Explanations

    words related to legal and judicial topics

    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
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    611
    +0.13
    0.5%
    19
    +0.13
    0.4%
    132
    +0.13
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.13
    0.08
    401
    +0.13
    0.06
    631
    +0.13
    0.05
    Negative Logits
     destro
    -1.05
     livest
    -1.03
    eworld
    -0.99
    uilt
    -0.96
     Azerb
    -0.95
     unsustainable
    -0.94
    ç
    -0.90
    onut
    -0.89
    ript
    -0.86
    obyl
    -0.86
    POSITIVE LOGITS
     Scalia
    1.46
     justices
    1.28
     Sonia
    1.13
    OTUS
    1.08
    letters
    1.06
    blog
    1.03
     Gorsuch
    1.02
    ervative
    1.00
     Justice
    0.99
     Brennan
    0.99
    Activations Density 1.090%

    No Known Activations