© 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. 8090
    Prev
    Next
    INDEX
    Explanations

    names or specific terms related to technology, public figures, and military equipment

    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
    99
    +0.18
    0.9%
    326
    +0.10
    0.5%
    68
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    326
    +0.18
    0.09
    99
    +0.10
    0.07
    514
    +0.10
    0.06
    Negative Logits
     Gujar
    -0.80
     nomine
    -0.77
    onica
    -0.77
    £ı
    -0.74
     metic
    -0.73
     circumstance
    -0.68
     incent
    -0.67
     Gingrich
    -0.66
    liction
    -0.64
    ãĥ¤
    -0.64
    POSITIVE LOGITS
    icz
    1.14
    orld
    1.08
    restling
    0.98
    ski
    0.97
    zee
    0.85
    orks
    0.82
    shaw
    0.81
    een
    0.80
    hair
    0.80
    rows
    0.80
    Activations Density 1.430%

    No Known Activations