© 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. 9998
    Prev
    Next
    INDEX
    Explanations

    references to political and social issues, particularly related to policies and conflicts

    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
    362
    +0.21
    1.0%
    393
    +0.17
    0.8%
    608
    +0.16
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    362
    +0.21
    0.12
    608
    +0.17
    0.10
    385
    +0.16
    0.08
    Negative Logits
     besides
    -0.95
    heit
    -0.91
    reau
    -0.74
    ubi
    -0.74
     distinguishes
    -0.74
     directs
    -0.74
     regulates
    -0.72
     communicates
    -0.72
    gans
    -0.69
    adj
    -0.69
    POSITIVE LOGITS
     collapse
    1.14
     emergence
    1.11
     breakup
    1.09
     latter
    1.08
     advent
    1.07
     debacle
    1.06
     aftermath
    1.06
     fateful
    1.06
     aforementioned
    1.06
     demise
    1.05
    Activations Density 0.375%

    No Known Activations