Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Feature Splitting for GPT2-Small
    3. GPT2-Small
    4. Residual Feature Splitting 24576
    5. 8-RES_FS24576-JB
    6. 12394
    Prev
    Next
    INDEX
    Explanations

    names of individuals in the entertainment industry and elements related to entertainment content creation

    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
    492
    +0.10
    0.5%
    190
    +0.10
    0.4%
    284
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    659
    +0.10
    0.05
    284
    +0.10
    0.05
    232
    +0.10
    0.05
    Negative Logits
    espie
    -0.79
     Bland
    -0.74
    umenthal
    -0.74
     Trinidad
    -0.67
    Colorado
    -0.66
     prov
    -0.66
     Palest
    -0.65
     Pell
    -0.65
     Rudd
    -0.65
     Gaul
    -0.64
    POSITIVE LOGITS
    atsu
    1.38
    ichi
    1.37
    osuke
    1.31
    ashi
    1.30
    uchi
    1.29
    oki
    1.29
    etsu
    1.29
    oshi
    1.28
    ikawa
    1.28
    iji
    1.27
    Activations Density 0.133%

    No Known Activations