© 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. 1422
    Prev
    Next
    INDEX
    Explanations

    locations or organizations related to specific entities or persons

    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
    447
    +0.23
    1.1%
    481
    +0.15
    0.7%
    314
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    232
    +0.23
    0.09
    659
    +0.15
    0.08
    314
    +0.11
    0.01
    Negative Logits
     thereof
    -0.80
     thereto
    -0.77
     respectively
    -0.69
    Ħ¢
    -0.66
     encomp
    -0.66
     guiIcon
    -0.65
     trans
    -0.65
     âĢ¦"
    -0.62
     guiActiveUnfocused
    -0.61
     rather
    -0.61
    POSITIVE LOGITS
    jamin
    0.98
    odore
    0.97
    ifax
    0.96
    resa
    0.95
    ston
    0.90
    xiety
    0.89
    olyn
    0.88
    lahoma
    0.87
    anyahu
    0.86
    hesda
    0.86
    Activations Density 0.477%

    No Known Activations