© 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. 23904
    Prev
    Next
    INDEX
    Explanations

    references to specific names in a context related to events or individuals

    oai_token-act-pair · gpt-4o-miniTriggered 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
    447
    +0.11
    0.5%
    272
    +0.09
    0.4%
    174
    +0.08
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    659
    +0.11
    0.04
    343
    +0.09
    0.03
    326
    +0.08
    0.03
    Negative Logits
    stairs
    -0.80
    sheet
    -0.80
    rons
    -0.79
    icle
    -0.78
    Ö¼
    -0.78
    ries
    -0.78
    ifiable
    -0.78
    theless
    -0.77
    rics
    -0.75
    itudes
    -0.73
    POSITIVE LOGITS
    vernment
    0.98
    emon
    0.86
     Libre
    0.78
    qt
    0.77
    veyard
    0.76
    ño
    0.73
     Haram
    0.73
    uchi
    0.71
    oths
    0.71
    pport
    0.71
    Activations Density 0.098%

    No Known Activations