© 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
    2. Joseph Bloom · Feature Splitting for GPT2-Small
    3. GPT2-Small
    4. Residual Feature Splitting 24576
    5. 8-RES_FS24576-JB
    6. 1307
    Prev
    Next
    INDEX
    Explanations

    proper nouns related to sports teams

    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
    566
    +0.11
    0.5%
    373
    +0.10
    0.5%
    269
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    751
    +0.11
    0.02
    269
    +0.10
    0.01
    677
    +0.10
    0.01
    Negative Logits
    Scale
    -0.72
    mpeg
    -0.70
    gerald
    -0.68
    Forward
    -0.67
    Bi
    -0.67
    Son
    -0.66
    opus
    -0.60
    osity
    -0.59
    Out
    -0.59
    Mini
    -0.59
    POSITIVE LOGITS
     reins
    0.87
     responsibility
    0.78
    lord
    0.77
     duties
    0.76
    ership
    0.76
    respons
    0.71
     respons
    0.70
    ordinate
    0.67
    erto
    0.67
     custody
    0.67
    Activations Density 0.028%

    No Known Activations