© 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. Joseph Bloom · Feature Splitting for GPT2-Small
    5. GPT2-Small
    7. Residual Feature Splitting 12288
    9. 8-RES_FS12288-JB
    11. 9844
    Prev
    Next
    INDEX
    Explanations

    mentions of the superhero character "Man"

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs12288-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_12288
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    12,288
    Data Type
    torch.float32
    Hook Point
    blocks.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    515
    +0.13
    0.6%
    314
    +0.10
    0.5%
    320
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    515
    +0.13
    0.04
    232
    +0.10
    0.03
    187
    +0.10
    0.03
    Negative Logits
    RIPT
    -0.75
    èĥ
    -0.71
    PsyNetMessage
    -0.69
    åī
    -0.66
    使
    -0.66
    ="#
    -0.63
    ENC
    -0.63
    âĨij
    -0.61
    èª
    -0.61
    è¦
    -0.61
    POSITIVE LOGITS
    uscript
    1.50
    hattan
    1.35
    fred
    1.33
    oeuv
    1.24
    ifest
    1.22
    agers
    1.16
    agements
    1.16
    hunt
    1.13
    osphere
    1.05
    iac
    1.04
    Activations Density 0.097%

    No Known Activations