© 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 49152
    9. 8-RES_FS49152-JB
    11. 37336
    Prev
    Next
    INDEX
    Explanations

    references to the name "Ohan" and the surname "Shankar" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs49152-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_49152
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    49,152
    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
    288
    +0.10
    0.4%
    406
    +0.09
    0.4%
    630
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    466
    +0.10
    0.01
    659
    +0.09
    0.01
    630
    +0.09
    0.00
    Negative Logits
    ongyang
    -0.94
    ©¶æ
    -0.92
    GoldMagikarp
    -0.88
    Ĥİ
    -0.72
    llah
    -0.72
    ŃĶ
    -0.70
    erto
    -0.69
    heric
    -0.69
    resents
    -0.68
    anooga
    -0.68
    POSITIVE LOGITS
    ovan
    1.05
     Singh
    0.99
    ansen
    0.83
    lein
    0.83
    lich
    0.77
    vale
    0.77
    ews
    0.76
    athan
    0.75
    thal
    0.75
     Lauder
    0.74
    Activations Density 0.003%

    No Known Activations