© 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 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. 9005
    Prev
    Next
    INDEX
    Explanations

    words related to legal actions and criminal offenses

    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
    278
    +0.11
    0.5%
    314
    +0.11
    0.5%
    211
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    278
    +0.11
    0.05
    225
    +0.11
    0.05
    484
    +0.10
    0.04
    Negative Logits
     Pony
    -0.73
     Rocket
    -0.72
    ocracy
    -0.68
     Gene
    -0.67
     Eid
    -0.66
    ERAL
    -0.65
     Cth
    -0.64
     Aqua
    -0.63
    achine
    -0.61
     Tasman
    -0.61
    POSITIVE LOGITS
    acles
    1.36
    chard
    1.33
    Else
    1.26
    acle
    1.20
    ifice
    1.11
    nam
    1.10
     Marketable
    1.04
    chid
    1.04
    lando
    0.98
    leans
    0.96
    Activations Density 0.095%

    No Known Activations