© 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. 35882
    Prev
    Next
    INDEX
    Explanations

    names related to people or characters

    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
    +0.17
    0.9%
    326
    +0.12
    0.6%
    543
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    173
    +0.17
    0.07
    179
    +0.12
    0.07
    167
    +0.10
    -0.06
    Negative Logits
    sburgh
    -1.02
    atcher
    -0.76
    cies
    -0.69
    fitting
    -0.68
    rontal
    -0.67
    sites
    -0.66
    uden
    -0.65
    atoon
    -0.64
    itude
    -0.63
    shire
    -0.61
    POSITIVE LOGITS
     Amend
    0.70
     Glover
    0.64
     Strait
    0.63
    mond
    0.62
     Meyer
    0.60
    bars
    0.60
     Boyle
    0.59
    Hamilton
    0.59
     Chau
    0.59
     DeV
    0.58
    Activations Density 9.960%

    No Known Activations