© 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. 20454
    Prev
    Next
    INDEX
    Explanations

    descriptions of art exhibitions and artworks

    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
    +0.14
    0.6%
    401
    +0.11
    0.5%
    18
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    401
    +0.14
    0.06
    76
    +0.11
    0.05
    18
    +0.11
    0.05
    Negative Logits
     ObamaCare
    -0.97
    amacare
    -0.93
     Obamacare
    -0.88
     timeout
    -0.85
     Comcast
    -0.82
    Senate
    -0.81
    votes
    -0.80
     CIS
    -0.76
    BIP
    -0.75
     Coinbase
    -0.75
    POSITIVE LOGITS
     paintings
    1.53
     sculptures
    1.52
     sculpture
    1.51
     artwork
    1.51
     painter
    1.49
     mural
    1.38
     artistic
    1.36
     artist
    1.33
     art
    1.33
     poetry
    1.29
    Activations Density 0.865%

    No Known Activations