© 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. 5973
    Prev
    Next
    INDEX
    Explanations

    reports of legal cases and criminal activities

    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
    260
    +0.12
    0.5%
    447
    +0.10
    0.5%
    209
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    651
    +0.12
    0.03
    209
    +0.10
    0.03
    540
    +0.10
    0.03
    Negative Logits
    asus
    -0.93
     embr
    -0.75
    retch
    -0.68
    argon
    -0.68
    wig
    -0.68
    pees
    -0.68
    sonian
    -0.67
    eworks
    -0.66
    ramid
    -0.66
     livest
    -0.66
    POSITIVE LOGITS
     involving
    1.16
     cases
    0.94
     occ
    0.75
    20439
    0.74
     occurring
    0.74
     Cases
    0.73
     cited
    0.73
    cases
    0.73
    idences
    0.73
     occurrence
    0.72
    Activations Density 0.075%

    No Known Activations