© 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. 33071
    Prev
    Next
    INDEX
    Explanations

    descriptions related to painting or applying paint

    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
    +0.14
    0.6%
    239
    +0.12
    0.5%
    7
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    526
    +0.14
    -0.04
    362
    +0.12
    0.11
    608
    +0.12
    0.17
    Negative Logits
    nesses
    -0.84
    AMY
    -0.83
    doms
    -0.82
    zbek
    -0.80
    PF
    -0.79
     htt
    -0.78
    aucus
    -0.77
    indal
    -0.77
    cgi
    -0.75
    ITED
    -0.74
    POSITIVE LOGITS
    brush
    1.21
     thinner
    1.08
     painting
    0.90
     painter
    0.90
     painted
    0.90
     paints
    0.87
    haps
    0.86
    wright
    0.86
    bats
    0.86
    pain
    0.86
    Activations Density 11.121%

    No Known Activations