© 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. 7481
    Prev
    Next
    INDEX
    Explanations

    information related to personal hygiene and health, focusing on hair care, shielding against radiation, and potential health risks caused by environmental factors

    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
    51
    +0.14
    0.6%
    218
    +0.10
    0.5%
    470
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    51
    +0.14
    0.05
    283
    +0.10
    0.02
    418
    +0.09
    0.04
    Negative Logits
    soDeliveryDate
    -0.91
    çīĪ
    -0.86
    ropolitan
    -0.82
    ourced
    -0.74
    ennial
    -0.73
    ãĤ«
    -0.71
    åŃ
    -0.70
    Commission
    -0.69
    LCS
    -0.68
    ARCH
    -0.67
    POSITIVE LOGITS
     wearer
    0.94
     untreated
    0.93
     ingest
    0.85
    soever
    0.84
     milliseconds
    0.82
     downstream
    0.80
     susceptible
    0.80
     slightest
    0.78
     bystanders
    0.74
     ingested
    0.73
    Activations Density 0.447%

    No Known Activations