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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & 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. 8346
    Prev
    Next
    INDEX
    Explanations

    distances, especially expressed in miles or kilometers

    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
    545
    +0.10
    0.5%
    589
    +0.08
    0.4%
    269
    +0.08
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    545
    +0.10
    0.03
    589
    +0.08
    0.03
    570
    +0.08
    0.02
    Negative Logits
     guiName
    -0.69
    anan
    -0.55
    isner
    -0.55
     stret
    -0.54
    ivalry
    -0.54
    onite
    -0.54
    EngineDebug
    -0.54
    Ban
    -0.53
     headlights
    -0.51
    winner
    -0.50
    POSITIVE LOGITS
    )!
    1.21
    )
    1.20
    ),"
    1.18
    )—
    1.10
    ),
    1.09
    )'
    1.06
    )-
    1.05
    )."
    1.02
    ).
    1.00
    /)
    0.97
    Activations Density 0.071%

    No Known Activations