© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 7450
    Prev
    Next
    INDEX
    Explanations

    phrases related to telecommunications and public policy discussions

    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
    519
    +0.11
    0.5%
    98
    +0.11
    0.5%
    457
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    566
    +0.11
    0.06
    718
    +0.11
    0.07
    8
    +0.10
    0.06
    Negative Logits
     earlier
    -0.70
    ilial
    -0.66
     Yesterday
    -0.66
     Recre
    -0.60
     Investigative
    -0.59
     Myster
    -0.58
     exting
    -0.58
     Previously
    -0.57
     sarc
    -0.57
     recalled
    -0.57
    POSITIVE LOGITS
     unbeat
    0.85
     outweigh
    0.81
    ecided
    0.77
     manageable
    0.73
     unstoppable
    0.72
    brainer
    0.70
     worthwhile
    0.69
     outwe
    0.67
    ]).
    0.66
     options
    0.66
    Activations Density 0.709%

    No Known Activations