© 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. 18630
    Prev
    Next
    INDEX
    Explanations

    mentions of books with different contexts, such as library-related discussions, reading recommendations, and book purchases

    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
    167
    +0.13
    0.6%
    651
    +0.11
    0.5%
    11
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    651
    +0.13
    0.03
    11
    +0.11
    0.02
    390
    +0.10
    0.02
    Negative Logits
    00200000
    -0.72
     Yin
    -0.70
    xon
    -0.69
    ntil
    -0.68
     Vital
    -0.66
    abwe
    -0.65
     Bots
    -0.64
    yip
    -0.64
    ilitary
    -0.64
    alty
    -0.62
    POSITIVE LOGITS
    stores
    1.37
    hel
    1.24
    shop
    1.15
    seller
    1.07
    books
    1.06
    worms
    1.05
    marks
    1.00
    worm
    1.00
    sell
    0.99
    reading
    0.94
    Activations Density 0.047%

    No Known Activations