© 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. 2125
    Prev
    Next
    INDEX
    Explanations

    phrases related to political discussions and policy proposals

    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
    87
    +0.16
    0.8%
    373
    +0.13
    0.6%
    756
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    121
    +0.16
    0.06
    426
    +0.13
    0.05
    238
    +0.12
    0.05
    Negative Logits
    Measure
    -0.61
    Oak
    -0.61
    ãĥĥãĥī
    -0.56
    Fit
    -0.53
    ample
    -0.52
    CLOSE
    -0.51
     diaper
    -0.51
     miscarriage
    -0.51
     Bigfoot
    -0.50
    mable
    -0.50
    POSITIVE LOGITS
     quoted
    0.91
     sarcast
    0.83
     quoting
    0.78
     referring
    0.77
     paraph
    0.71
     rhet
    0.70
     told
    0.70
     Said
    0.68
     citing
    0.67
     wrote
    0.66
    Activations Density 0.208%

    No Known Activations