© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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 12288
    9. 8-RES_FS12288-JB
    11. 1840
    Prev
    Next
    INDEX
    Explanations

    information related to professions and fields of study

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs12288-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_12288
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    12,288
    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
    481
    +0.20
    0.9%
    40
    +0.10
    0.5%
    288
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.20
    0.09
    40
    +0.10
    0.07
    575
    +0.10
    0.08
    Negative Logits
    headers
    -0.71
    llah
    -0.68
    amaz
    -0.65
    endars
    -0.61
     backups
    -0.61
     Mald
    -0.60
    borough
    -0.60
    sites
    -0.59
    printed
    -0.58
    enda
    -0.58
    POSITIVE LOGITS
     synonymous
    0.85
    horse
    0.82
     known
    0.78
     whereby
    0.75
     invented
    0.75
     called
    0.75
     shorthand
    0.75
    icity
    0.74
     pioneered
    0.73
     commonly
    0.72
    Activations Density 0.572%

    No Known Activations