© 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 24576
    9. 8-RES_FS24576-JB
    11. 7973
    Prev
    Next
    INDEX
    Explanations

    political news and statements from politicians

    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
    373
    +0.16
    0.7%
    362
    +0.10
    0.5%
    248
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    280
    +0.16
    0.02
    284
    +0.10
    0.01
    362
    +0.10
    0.02
    Negative Logits
    ioch
    -0.63
    ihar
    -0.63
    suggest
    -0.61
    bec
    -0.60
     Zup
    -0.59
    puff
    -0.57
    ides
    -0.56
    educ
    -0.55
    bley
    -0.55
    gur
    -0.55
    POSITIVE LOGITS
     art
    0.78
     affairs
    0.70
    azeera
    0.68
     Decay
    0.65
    senal
    0.62
    resp
    0.61
    lict
    0.61
     entreprene
    0.60
     matter
    0.59
     world
    0.57
    Activations Density 0.028%

    No Known Activations