© 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 24576
    9. 8-RES_FS24576-JB
    11. 18838
    Prev
    Next
    INDEX
    Explanations

    information related to technology, specifically in the context of music production and Bitcoin/crypto

    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
    87
    +0.19
    0.9%
    459
    +0.17
    0.8%
    605
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    459
    +0.19
    0.06
    119
    +0.17
    0.04
    184
    +0.10
    0.03
    Negative Logits
     Plaint
    -0.67
    judicial
    -0.60
     Reconstruction
    -0.60
     riots
    -0.60
     redacted
    -0.59
     Democr
    -0.59
     mutated
    -0.58
     Confederacy
    -0.58
     Plaintiff
    -0.58
     inco
    -0.58
    POSITIVE LOGITS
     beginner
    0.98
     personalized
    0.94
    your
    0.94
     DIY
    0.89
     your
    0.89
     Yourself
    0.89
     yourself
    0.89
     browse
    0.89
    Learn
    0.86
     YOUR
    0.86
    Activations Density 0.805%

    No Known Activations