© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Feature Splitting for GPT2-Small
    5. GPT2-Small
    7. Residual Feature Splitting 24576
    9. 8-RES_FS24576-JB
    11. 22187
    Prev
    Next
    INDEX
    Explanations

    references to specific individuals, particularly those named "Paul" and "Joseph."

    oai_token-act-pair · gpt-4o-miniTriggered 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
    373
    +0.09
    0.5%
    209
    +0.09
    0.4%
    287
    +0.08
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    659
    +0.09
    0.04
    232
    +0.09
    0.03
    525
    +0.08
    0.03
    Negative Logits
    omore
    -0.74
    sterdam
    -0.69
    ammy
    -0.66
    RGB
    -0.62
    atem
    -0.61
    ataka
    -0.61
    coming
    -0.61
    aryn
    -0.61
    reach
    -0.60
    alach
    -0.59
    POSITIVE LOGITS
    ãĥ¼ãĥĨ
    0.66
     Cable
    0.63
     ãĤµãĥ¼ãĥĨãĤ£ãĥ¯ãĥ³
    0.63
     Levant
    0.56
     Soldiers
    0.53
     Falcon
    0.52
     ASCII
    0.52
    代
    0.52
    åĩ
    0.52
    ç·
    0.52
    Activations Density 0.138%

    No Known Activations