© 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. 35469
    Prev
    Next
    INDEX
    Explanations

    programming-related terms and code snippets

    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
    622
    +0.11
    0.5%
    267
    +0.10
    0.4%
    48
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    362
    +0.11
    0.10
    97
    +0.10
    0.05
    354
    +0.10
    0.07
    Negative Logits
    icles
    -0.79
    glass
    -0.76
    orial
    -0.76
    manship
    -0.75
    uality
    -0.75
    imental
    -0.73
    alist
    -0.73
    chell
    -0.73
    alia
    -0.72
    eer
    -0.71
    POSITIVE LOGITS
    fty
    1.07
    zzi
    1.04
    pper
    0.95
    ppy
    0.93
    oping
    0.92
    zzle
    0.91
    tto
    0.91
    ffe
    0.86
    ppo
    0.85
    zona
    0.82
    Activations Density 7.288%

    No Known Activations