© 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 EvalsExportsinterp-engineNEWAPI 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. 4994
    Prev
    Next
    INDEX
    Explanations

    details about books or movies, particularly focusing on titles, authors, genres, and plot summaries

    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
    447
    +0.16
    0.7%
    481
    +0.14
    0.7%
    499
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    499
    +0.16
    0.05
    736
    +0.14
    0.05
    582
    +0.12
    0.03
    Negative Logits
     spons
    -0.77
     Flickr
    -0.77
     credential
    -0.75
     podium
    -0.72
    elong
    -0.71
     confer
    -0.71
     donor
    -0.70
    ype
    -0.70
     Cosponsors
    -0.70
     mailing
    -0.67
    POSITIVE LOGITS
     thriller
    1.30
     sequel
    1.17
     trilogy
    1.15
     novels
    1.11
     Chronicles
    1.06
     dystopian
    1.05
     Trilogy
    0.98
     dystop
    0.96
     protagonist
    0.96
     anthology
    0.95
    Activations Density 0.861%

    No Known Activations