© 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 1536
    9. 8-RES_FS1536-JB
    11. 1138
    Prev
    Next
    INDEX
    Explanations

    positive attributes or characteristics attributed to individuals

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs1536-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_1536
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    1,536
    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
    496
    +0.12
    0.5%
    230
    +0.10
    0.4%
    616
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    237
    +0.12
    0.05
    163
    +0.10
    0.05
    458
    +0.10
    0.05
    Negative Logits
    olas
    -0.77
    phabet
    -0.77
    dict
    -0.69
    ees
    -0.64
    isson
    -0.64
     Pru
    -0.60
     Jah
    -0.59
     Papers
    -0.59
     Graves
    -0.58
    eh
    -0.58
    POSITIVE LOGITS
    THING
    1.60
     conceivable
    1.41
     imaginable
    1.31
    where
    1.21
     single
    1.07
    single
    1.04
     inch
    1.03
    WHERE
    0.98
     ounce
    0.97
    thin
    0.96
    Activations Density 0.552%

    No Known Activations