© 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. 11910
    Prev
    Next
    INDEX
    Explanations

    phrases related to surveys and statistics in articles

    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
    +0.31
    1.6%
    597
    +0.09
    0.5%
    756
    +0.09
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    566
    +0.31
    0.09
    87
    +0.09
    -0.02
    49
    +0.09
    0.06
    Negative Logits
     ministries
    -0.67
    Dialogue
    -0.65
     Pos
    -0.63
     clarified
    -0.60
     mediation
    -0.60
     hierarchical
    -0.60
     clar
    -0.59
    leaders
    -0.59
     disbanded
    -0.59
     stabilization
    -0.58
    POSITIVE LOGITS
     browsing
    0.89
     downloading
    0.80
     subscribing
    0.79
     surfing
    0.78
     binge
    0.78
     subscribed
    0.77
     consume
    0.76
     buying
    0.73
     shopping
    0.73
     browse
    0.73
    Activations Density 0.948%

    No Known Activations