© 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. 32943
    Prev
    Next
    INDEX
    Explanations

    technical and instructional information

    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
    +0.27
    1.3%
    680
    +0.09
    0.4%
    38
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    314
    +0.27
    -0.11
    659
    +0.09
    0.14
    232
    +0.09
    0.11
    Negative Logits
    yond
    -0.60
    é¾įå¥ij士
    -0.59
    +.
    -0.57
    $.
    -0.57
    !.
    -0.55
    é¾įå
    -0.55
     rather
    -0.54
    `.
    -0.54
    Ĭ±
    -0.53
    ĨĴ
    -0.53
    POSITIVE LOGITS
     consists
    0.69
     comprises
    0.62
    iest
    0.61
    hest
    0.60
     consisted
    0.60
     dilemma
    0.59
     represents
    0.59
    undown
    0.58
     portion
    0.57
     extends
    0.57
    Activations Density 23.860%

    No Known Activations