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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 21112
    Prev
    Next
    INDEX
    Explanations

    expressions related to control or lack of control over circumstances

    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
    745
    +0.13
    0.6%
    277
    +0.10
    0.5%
    228
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    298
    +0.13
    0.03
    641
    +0.10
    0.03
    635
    +0.10
    0.02
    Negative Logits
     AGA
    -0.73
    uala
    -0.70
     Ahead
    -0.69
     ALSO
    -0.69
    MpServer
    -0.63
     Nanto
    -0.63
     Across
    -0.62
     Shinzo
    -0.62
     Falling
    -0.62
     Cancel
    -0.61
    POSITIVE LOGITS
     confines
    1.47
     bounds
    1.45
     boundaries
    1.31
     borders
    1.14
     limits
    1.12
     realm
    1.05
     realms
    1.01
     comprehension
    0.96
     scope
    0.95
     limitations
    0.89
    Activations Density 0.177%

    No Known Activations