© 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. 19776
    Prev
    Next
    INDEX
    Explanations

    code-related terms related to working with files and data in Python

    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
    447
    +0.18
    0.8%
    737
    +0.13
    0.6%
    376
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    227
    +0.18
    0.02
    570
    +0.13
    0.01
    737
    +0.10
    0.04
    Negative Logits
    Reloaded
    -0.71
    parency
    -0.67
    pun
    -0.66
    afort
    -0.65
    utsu
    -0.65
    ival
    -0.63
    agy
    -0.63
    negie
    -0.63
     loopholes
    -0.63
     Ukrain
    -0.62
    POSITIVE LOGITS
     Suppose
    0.93
     XY
    0.92
     foo
    0.91
    foo
    0.85
     suppose
    0.74
    example
    0.70
     neighbor
    0.66
     \(
    0.65
     hello
    0.65
     cafeteria
    0.65
    Activations Density 0.786%

    No Known Activations