© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 20521
    Prev
    Next
    INDEX
    Explanations

    terms related to government, regulation, and policy in the context of various industries

    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
    +0.16
    0.7%
    752
    +0.10
    0.4%
    305
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.16
    0.08
    146
    +0.10
    0.07
    681
    +0.10
    0.06
    Negative Logits
    astery
    -0.77
    tics
    -0.73
    minus
    -0.73
    selves
    -0.72
    ebus
    -0.70
    atha
    -0.67
    wo
    -0.67
    ãĤ¨ãĥ«
    -0.65
    oute
    -0.65
    urgy
    -0.63
    POSITIVE LOGITS
     regulators
    0.99
     mandated
    0.94
     decree
    0.94
     forb
    0.90
     approvals
    0.87
     cens
    0.87
     funding
    0.87
     intervened
    0.86
     approved
    0.85
     regulations
    0.85
    Activations Density 0.516%

    No Known Activations