© 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. 306
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "autograph" or its variants

    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
    575
    +0.11
    0.5%
    288
    +0.11
    0.5%
    754
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    701
    +0.11
    0.02
    754
    +0.11
    0.02
    396
    +0.10
    0.02
    Negative Logits
    BLE
    -0.81
     Forbidden
    -0.71
    lihood
    -0.70
     Soda
    -0.70
    imaru
    -0.70
    forth
    -0.70
    FORE
    -0.69
    edin
    -0.68
    DER
    -0.68
    ewski
    -0.67
    POSITIVE LOGITS
    ographs
    1.33
    ograph
    1.32
    umn
    1.19
    ographed
    1.14
    opsy
    1.13
    onomous
    1.07
    omatic
    1.06
    ocom
    1.04
    oly
    1.02
    ogyn
    1.00
    Activations Density 0.056%

    No Known Activations