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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    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. 7808
    Prev
    Next
    INDEX
    Explanations

    web technologies and platforms

    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
    167
    +0.12
    0.5%
    385
    +0.10
    0.4%
    326
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    326
    +0.12
    0.01
    269
    +0.10
    0.01
    525
    +0.09
    0.01
    Negative Logits
    mble
    -0.86
    SPONSORED
    -0.85
    iour
    -0.80
    liness
    -0.79
    orp
    -0.73
    ISION
    -0.71
    agonist
    -0.68
    jri
    -0.68
    byter
    -0.66
    Ö¼
    -0.66
    POSITIVE LOGITS
     Carbuncle
    0.81
     Flask
    0.78
    Mine
    0.78
     gems
    0.77
     Ridge
    0.76
     Gems
    0.74
    claw
    0.73
    Ruby
    0.72
     Peaks
    0.72
    Bee
    0.72
    Activations Density 0.017%

    No Known Activations