© 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
    2. Joseph Bloom · Feature Splitting for GPT2-Small
    3. GPT2-Small
    4. Residual Feature Splitting 24576
    5. 8-RES_FS24576-JB
    6. 9405
    Prev
    Next
    INDEX
    Explanations

    mentions of specific political figures

    oai_token-act-pair · gpt-3.5-turboTriggered 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
    745
    +0.11
    0.5%
    675
    +0.09
    0.4%
    357
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    675
    +0.11
    0.08
    442
    +0.09
    0.07
    293
    +0.09
    0.07
    Negative Logits
     Fuji
    -0.69
     Mirage
    -0.62
     Yam
    -0.61
     Samar
    -0.61
     towns
    -0.60
     casc
    -0.59
     Palm
    -0.58
     Tasman
    -0.58
     Gaul
    -0.57
     blitz
    -0.57
    POSITIVE LOGITS
    t
    1.00
    ï¸ı
    0.96
    ude
    0.94
    agree
    0.93
    ve
    0.93
    vable
    0.92
    sic
    0.90
    ember
    0.89
    tal
    0.88
    ti
    0.88
    Activations Density 0.155%

    No Known Activations