© 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 Local
    9. 6-RES_SCL-AJT
    11. 36266
    Prev
    Next
    INDEX
    Explanations

    terms related to laws or regulations and policies

    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
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    447
    +0.25
    1.3%
    481
    +0.19
    1.0%
    393
    +0.14
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    640
    +0.25
    0.30
    393
    +0.19
    0.25
    250
    +0.14
    0.09
    Negative Logits
    ucci
    -0.68
    ashtra
    -0.61
     portrayal
    -0.60
    Catalog
    -0.55
    é¾įåĸļ士
    -0.54
     ancest
    -0.53
    igue
    -0.53
    acci
    -0.53
    onge
    -0.53
     perspect
    -0.53
    POSITIVE LOGITS
     hostilities
    0.63
    glas
    0.60
    xit
    0.56
     fresh
    0.53
     these
    0.52
    rians
    0.51
     Goods
    0.50
     Calm
    0.49
    ammad
    0.49
     Moves
    0.48
    Activations Density 10.567%

    No Known Activations