© 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 24576
    9. 8-RES_FS24576-JB
    11. 1525
    Prev
    Next
    INDEX
    Explanations

    proper nouns, especially names of people

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs24576-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_24576
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    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
    373
    +0.13
    0.6%
    530
    +0.11
    0.5%
    213
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    530
    +0.13
    0.05
    326
    +0.11
    0.04
    406
    +0.10
    0.05
    Negative Logits
    ciplinary
    -0.70
    ecycle
    -0.70
     Sea
    -0.67
    agate
    -0.67
    unct
    -0.66
    ghai
    -0.66
    tons
    -0.65
    ctr
    -0.63
    cation
    -0.63
    idae
    -0.62
    POSITIVE LOGITS
    MAN
    1.45
    IAN
    1.41
    SON
    1.40
    LEY
    1.39
    TON
    1.39
    HAEL
    1.37
    FIL
    1.36
    WOR
    1.36
    WOOD
    1.33
    ELL
    1.33
    Activations Density 0.139%

    No Known Activations