© 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. 1398
    Prev
    Next
    INDEX
    Explanations

    expressions of disagreement or disbelief

    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
    314
    +0.10
    0.5%
    745
    +0.10
    0.5%
    514
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    675
    +0.10
    0.06
    759
    +0.10
    0.06
    514
    +0.09
    0.06
    Negative Logits
     Broadcasting
    -0.69
     CLR
    -0.68
     Trinidad
    -0.68
     Rosenthal
    -0.68
     scattering
    -0.67
     adolesc
    -0.66
    ickets
    -0.64
     Transparency
    -0.64
     friction
    -0.64
     Avalon
    -0.64
    POSITIVE LOGITS
    own
    1.12
    ï¸ı
    1.04
    should
    1.01
    agree
    0.99
    swer
    0.99
    must
    0.98
    tal
    0.96
    ve
    0.93
    audi
    0.91
     deserve
    0.88
    Activations Density 0.142%

    No Known Activations