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. 25753
    Prev
    Next
    INDEX
    Explanations

    instances of URLs or web address paths

    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
    393
    +0.10
    0.5%
    766
    +0.10
    0.4%
    665
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    445
    +0.10
    0.02
    605
    +0.10
    0.01
    97
    +0.10
    0.01
    Negative Logits
     hurled
    -0.90
     conveyed
    -0.82
     flung
    -0.71
     thereof
    -0.71
     employed
    -0.68
     struck
    -0.67
     tossed
    -0.66
    ointed
    -0.66
     nailed
    -0.65
     delivered
    -0.65
    POSITIVE LOGITS
     www
    1.10
     Settings
    1.00
     Downloads
    0.92
     Preferences
    0.85
     http
    0.81
     Documents
    0.75
     Menu
    0.71
     Archives
    0.70
     iTunes
    0.70
     Elections
    0.69
    Activations Density 0.034%

    No Known Activations