© 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. 8652
    Prev
    Next
    INDEX
    Explanations

    mentions of legal proceedings and investigations

    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
    127
    +0.13
    0.5%
    503
    +0.11
    0.4%
    699
    +0.11
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    127
    +0.13
    0.12
    402
    +0.11
    0.11
    199
    +0.11
    0.12
    Negative Logits
    wagen
    -0.93
     shroud
    -0.81
    aimon
    -0.79
     Marble
    -0.77
    creen
    -0.75
     detached
    -0.73
     Belg
    -0.70
     Doodle
    -0.69
    hiro
    -0.68
    ITNESS
    -0.67
    POSITIVE LOGITS
    ł
    1.28
    ¹
    1.26
    IJ
    1.16
    ª
    1.14
    Ĵ
    1.09
    ij
    1.08
    Ķ
    1.07
    ľ
    0.99
    ©
    0.97
    ı
    0.94
    Activations Density 0.731%

    No Known Activations