© 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. 7293
    Prev
    Next
    INDEX
    Explanations

    instructions or information about performing exercise movements correctly

    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
    678
    +0.17
    0.7%
    5
    +0.11
    0.5%
    424
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    678
    +0.17
    0.05
    326
    +0.11
    0.06
    570
    +0.10
    0.01
    Negative Logits
     Chern
    -0.85
     unaff
    -0.82
     billionaires
    -0.82
    license
    -0.82
    Government
    -0.81
     cybersecurity
    -0.79
     Franchise
    -0.78
     Governments
    -0.78
     Markets
    -0.77
     licences
    -0.77
    POSITIVE LOGITS
     muscles
    1.14
     Technique
    1.11
     rhyth
    1.11
     posture
    1.10
     alternating
    1.10
     perpendicular
    1.06
     hips
    1.05
     lateral
    1.01
     cardio
    0.99
     rhythm
    0.98
    Activations Density 0.527%

    No Known Activations