© 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. 34785
    Prev
    Next
    INDEX
    Explanations

    mentions of accounts, means, and various measures or standards being discussed or compared

    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
    418
    +0.08
    0.5%
    114
    +0.07
    0.4%
    612
    +0.07
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    575
    +0.08
    0.16
    288
    +0.07
    0.19
    27
    +0.07
    0.09
    Negative Logits
     Rost
    -0.55
    agra
    -0.53
     Poe
    -0.50
     Binding
    -0.47
    ILA
    -0.47
    hib
    -0.46
    stown
    -0.46
    entin
    -0.46
    olded
    -0.46
    yrics
    -0.45
    POSITIVE LOGITS
     imaginable
    1.04
     conceivable
    0.78
     alike
    0.69
     except
    0.68
     whatsoever
    0.68
    cale
    0.61
     viz
    0.59
    Camera
    0.58
    rencies
    0.56
    except
    0.56
    Activations Density 5.864%

    No Known Activations