© 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. 20808
    Prev
    Next
    INDEX
    Explanations

    text related to law enforcement activities and personnel

    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
    +0.12
    0.5%
    58
    +0.11
    0.5%
    136
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    492
    +0.12
    0.04
    762
    +0.11
    0.06
    58
    +0.10
    0.03
    Negative Logits
    ))))
    -0.76
    iru
    -0.70
    )))
    -0.63
    comes
    -0.59
    ITNESS
    -0.57
    âĵĺ
    -0.56
     âĵĺ
    -0.56
    orio
    -0.56
    onga
    -0.56
    window
    -0.55
    POSITIVE LOGITS
     since
    1.42
     lately
    1.35
     countless
    1.05
     awhile
    1.04
     throughout
    1.01
     intermitt
    0.99
     extensively
    0.96
     unsuccessfully
    0.93
    since
    0.93
     spor
    0.91
    Activations Density 0.490%

    No Known Activations