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. 25674
    Prev
    Next
    INDEX
    Explanations

    mentions of video games and their titles

    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
    360
    +0.11
    0.5%
    167
    +0.10
    0.5%
    621
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    360
    +0.11
    0.02
    621
    +0.10
    0.02
    336
    +0.10
    0.01
    Negative Logits
    iffe
    -0.87
    etheless
    -0.78
    ancies
    -0.75
    orate
    -0.72
     derailed
    -0.70
    terday
    -0.69
    allel
    -0.69
    ibly
    -0.68
    ishable
    -0.67
    ought
    -0.67
    POSITIVE LOGITS
    cube
    1.14
    play
    1.14
    FAQ
    1.03
    Cube
    1.01
    Maker
    0.99
    cock
    0.99
    wright
    0.93
    pad
    0.92
    Spot
    0.92
    Stop
    0.90
    Activations Density 0.017%

    No Known Activations