© 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. 315
    Prev
    Next
    INDEX
    Explanations

    contact information, corporate addresses, and legal statements

    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
    612
    +0.16
    0.5%
    373
    +0.15
    0.5%
    276
    +0.12
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    326
    +0.16
    0.08
    232
    +0.15
    0.05
    288
    +0.12
    0.08
    Negative Logits
     Flavoring
    -1.11
    nces
    -1.06
    itals
    -1.01
    furt
    -1.00
    RAW
    -0.99
    lly
    -0.95
    resents
    -0.94
    lies
    -0.92
    xual
    -0.91
    LY
    -0.90
    POSITIVE LOGITS
    ipop
    1.41
    ega
    1.20
    eson
    1.07
    ingen
    0.96
    oning
    0.95
    sburgh
    0.95
    shire
    0.94
    ODUCT
    0.94
    ugi
    0.88
    itory
    0.87
    Activations Density 1.295%

    No Known Activations