© 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. 26532
    Prev
    Next
    INDEX
    Explanations

    occurrences of the term "gorilla" 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
    754
    +0.11
    0.5%
    343
    +0.11
    0.5%
    481
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    99
    +0.11
    0.01
    343
    +0.11
    0.01
    659
    +0.09
    0.01
    Negative Logits
    paren
    -0.83
    ply
    -0.80
    ensible
    -0.80
    log
    -0.78
    daq
    -0.78
    schild
    -0.75
    leness
    -0.72
    orough
    -0.71
    iosyn
    -0.71
    mare
    -0.69
    POSITIVE LOGITS
    ieri
    0.98
    istas
    0.88
     Haram
    0.82
    esi
    0.82
    usk
    0.79
     Ammunition
    0.79
    ñ
    0.78
    ista
    0.76
    ume
    0.76
    ength
    0.75
    Activations Density 0.006%

    No Known Activations