© 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. 721
    Prev
    Next
    INDEX
    Explanations

    financial terms and market-related information

    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
    642
    +0.11
    0.5%
    459
    +0.11
    0.5%
    724
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.11
    0.01
    461
    +0.11
    0.01
    710
    +0.09
    0.01
    Negative Logits
    76561
    -0.82
    hig
    -0.79
    cig
    -0.71
    senal
    -0.69
    metic
    -0.69
    shit
    -0.69
     narc
    -0.65
     cloaked
    -0.64
    resent
    -0.64
    activate
    -0.64
    POSITIVE LOGITS
     Catalog
    0.96
     deviation
    0.93
     Format
    0.86
     Definition
    0.85
     deviations
    0.84
     Template
    0.83
     Chart
    0.79
    ization
    0.78
     Errors
    0.77
    ity
    0.74
    Activations Density 0.020%

    No Known Activations