© 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. 11053
    Prev
    Next
    INDEX
    Explanations

    information related to health risks associated with certain behaviors or conditions

    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
    511
    +0.11
    0.5%
    156
    +0.10
    0.5%
    574
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    511
    +0.11
    0.03
    747
    +0.10
    0.02
    285
    +0.09
    0.02
    Negative Logits
    issance
    -0.84
     Dick
    -0.69
    åħī
    -0.69
     Crane
    -0.65
    SEC
    -0.64
    utra
    -0.64
     Edison
    -0.63
     Daylight
    -0.62
    Dick
    -0.62
    steel
    -0.62
    POSITIVE LOGITS
     allele
    0.93
     factors
    0.91
     behaviours
    0.85
    ogenic
    0.84
     behaviors
    0.82
     predis
    0.81
     factor
    0.81
     relapse
    0.80
     mortality
    0.76
     psychosis
    0.74
    Activations Density 0.039%

    No Known Activations