© 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
    3. Joseph Bloom · Feature Splitting for GPT2-Small
    5. GPT2-Small
    7. Residual Feature Splitting 12288
    9. 8-RES_FS12288-JB
    11. 316
    Prev
    Next
    INDEX
    Explanations

    business and financial terms and concepts

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs12288-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_12288
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    12,288
    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
    87
    +0.22
    1.1%
    481
    +0.19
    1.0%
    447
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.22
    0.14
    325
    +0.19
    0.07
    652
    +0.12
    0.06
    Negative Logits
     Marketable
    -0.61
     Unloaded
    -0.57
     Converted
    -0.57
     Arabia
    -0.56
     Pradesh
    -0.55
    TPS
    -0.55
     Ltd
    -0.54
    à¼
    -0.54
    ADVERTISEMENT
    -0.53
    )=(
    -0.53
    POSITIVE LOGITS
    iest
    1.13
    liest
    1.03
    osphere
    0.92
     portion
    0.89
     aspect
    0.89
    ultimate
    0.80
     hypothesis
    0.79
     analogy
    0.74
     fallacy
    0.73
     angle
    0.72
    Activations Density 1.246%

    No Known Activations