© 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. 6928
    Prev
    Next
    INDEX
    Explanations

    terms related to legal or justice matters, including terms related to public policy discussions and investigations

    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
    314
    +0.16
    0.7%
    615
    +0.11
    0.5%
    120
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    232
    +0.16
    0.06
    314
    +0.11
    0.01
    615
    +0.10
    0.03
    Negative Logits
    theless
    -0.98
     sprung
    -0.78
     silenced
    -0.78
     chuck
    -0.78
     ripple
    -0.75
     unison
    -0.74
     upside
    -0.74
     mockery
    -0.73
     fed
    -0.73
     broccoli
    -0.71
    POSITIVE LOGITS
    istries
    1.13
    Services
    1.04
    bernatorial
    1.03
    abulary
    1.02
    ilitation
    1.02
    iciency
    1.00
    artment
    0.99
    icultural
    0.99
    orers
    0.98
    mbudsman
    0.96
    Activations Density 0.188%

    No Known Activations