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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Apollo Research · Taylor · Identifying Functionally Important Features with End-to-End Sparse Dictionary Learning
    3. GPT2-Small
    4. Residual Similar CE E2E Recon
    5. 6-RES_SCEFR-AJT
    6. 13381
    Prev
    Next
    INDEX
    Explanations

    terms related to specific body parts, particularly the neck, and items or actions concerning the neck like lifting or injuries

    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
    587
    +0.19
    0.6%
    288
    +0.17
    0.6%
    285
    +0.16
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.19
    0.09
    181
    +0.17
    0.06
    659
    +0.16
    0.05
    Negative Logits
    urity
    -1.16
     Mile
    -1.04
     Flavoring
    -1.03
    ========
    -1.03
    ioch
    -0.98
    venants
    -0.97
    ISE
    -0.93
    anqu
    -0.92
    imaru
    -0.91
    ordinary
    -0.91
    POSITIVE LOGITS
    lace
    1.82
    tie
    1.67
    beard
    1.63
    lines
    1.61
    bone
    1.48
    line
    1.45
    bones
    1.42
    yard
    1.32
    guards
    1.17
    yards
    1.14
    Activations Density 1.029%

    No Known Activations