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 49152
    5. 8-RES_FS49152-JB
    6. 41472
    Prev
    Next
    INDEX
    Explanations

    titles and roles related to academic positions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs49152-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_49152
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    49,152
    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
    224
    +0.11
    0.5%
    288
    +0.10
    0.5%
    415
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    224
    +0.11
    0.02
    687
    +0.10
    0.01
    104
    +0.10
    0.01
    Negative Logits
    nikov
    -0.75
     smugglers
    -0.74
    ighters
    -0.70
     Labrador
    -0.69
     mileage
    -0.67
     armoured
    -0.66
     IMAGES
    -0.66
    psons
    -0.65
    bley
    -0.65
     launchers
    -0.64
    POSITIVE LOGITS
     emer
    1.01
    iate
    0.95
     dean
    0.94
    onym
    0.88
    llor
    0.83
    ials
    0.82
    uthor
    0.81
    ipal
    0.81
     Graduate
    0.78
    jay
    0.77
    Activations Density 0.023%

    No Known Activations