© 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. 37289
    Prev
    Next
    INDEX
    Explanations

    words related to horses and horse-related terminology

    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
    428
    +0.10
    0.5%
    232
    +0.10
    0.4%
    151
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    284
    +0.10
    0.01
    428
    +0.10
    0.01
    232
    +0.10
    0.01
    Negative Logits
    REDACTED
    -0.77
    ERC
    -0.74
    Ô
    -0.71
    FactoryReloaded
    -0.70
     admitting
    -0.70
    ãģ®éŃĶ
    -0.68
    ħĭ
    -0.68
    piracy
    -0.63
    PsyNetMessage
    -0.62
    Favorite
    -0.62
    POSITIVE LOGITS
    izons
    1.70
    oscope
    1.09
    rid
    1.08
    osc
    1.02
    cru
    0.94
    seless
    0.91
    itas
    0.90
    izon
    0.88
    ror
    0.84
    gin
    0.79
    Activations Density 0.002%

    No Known Activations