© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 4134
    Prev
    Next
    INDEX
    Explanations

    quotes or statements made by individuals

    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
    +0.10
    0.4%
    536
    +0.10
    0.4%
    541
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    274
    +0.10
    0.12
    283
    +0.10
    0.04
    70
    +0.10
    0.11
    Negative Logits
    earances
    -0.77
    aphael
    -0.75
    hoff
    -0.74
    ption
    -0.71
    theless
    -0.66
    ammy
    -0.65
    hern
    -0.65
    ————
    -0.64
    cific
    -0.64
    ohyd
    -0.64
    POSITIVE LOGITS
     deems
    0.76
    XM
    0.73
    ©¶æ¥µ
    0.72
    ij士
    0.70
     deem
    0.70
    IONS
    0.68
    é¾
    0.67
    ¾
    0.64
     represents
    0.64
    ought
    0.64
    Activations Density 6.727%

    No Known Activations