© 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 EvalsExportsAPI 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. 915
    Prev
    Next
    INDEX
    Explanations

    instances of the word "vest" or variations of it

    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
    288
    +0.17
    0.6%
    270
    +0.13
    0.5%
    459
    +0.13
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.17
    0.09
    326
    +0.13
    0.07
    404
    +0.13
    0.05
    Negative Logits
    avez
    -0.91
    uddin
    -0.88
    inks
    -0.87
    fix
    -0.86
    Correct
    -0.85
    éĹĺ
    -0.81
    realDonaldTrump
    -0.80
    king
    -0.79
    wark
    -0.79
    figure
    -0.78
    POSITIVE LOGITS
    eering
    1.22
    igation
    1.20
    igators
    1.20
    igator
    1.12
    igious
    1.05
    ige
    1.03
    rette
    1.02
    rils
    0.99
     vest
    0.98
    iture
    0.96
    Activations Density 0.842%

    No Known Activations