© 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. 6559
    Prev
    Next
    INDEX
    Explanations

    references to specific actions or events

    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
    616
    +0.15
    0.7%
    540
    +0.11
    0.5%
    539
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    616
    +0.15
    0.12
    251
    +0.11
    0.10
    503
    +0.10
    0.07
    Negative Logits
    DragonMagazine
    -0.76
     Annotations
    -0.76
    hyde
    -0.73
     Rica
    -0.73
     Controls
    -0.70
     Flake
    -0.69
     Favor
    -0.68
     Challenges
    -0.68
    Kit
    -0.68
    Ô
    -0.67
    POSITIVE LOGITS
    iest
    1.25
    acious
    1.08
    liest
    1.03
    itial
    1.01
    uper
    0.98
    most
    0.94
    rep
    0.93
    auc
    0.90
    pless
    0.89
    ocratic
    0.88
    Activations Density 3.434%

    No Known Activations