© 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. 8790
    Prev
    Next
    INDEX
    Explanations

    information related to schedules and events, including deadlines and pick-up details

    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
    480
    +0.49
    2.5%
    266
    +0.16
    0.8%
    87
    +0.15
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    480
    +0.49
    0.03
    266
    +0.16
    0.10
    739
    +0.15
    0.03
    Negative Logits
    ĸļ
    -0.68
    uably
    -0.67
    ãĤ©
    -0.64
     metaphors
    -0.63
    ãĥ³ãĤ¸
    -0.57
     ubiquitous
    -0.56
     overshadow
    -0.56
     crammed
    -0.55
     yawn
    -0.55
     grinning
    -0.55
    POSITIVE LOGITS
     Submit
    0.98
     Cancel
    0.96
     notification
    0.94
     Payment
    0.94
     Login
    0.91
     Sponsor
    0.91
     Warranty
    0.89
     Password
    0.87
     Regist
    0.87
     warranty
    0.86
    Activations Density 1.006%

    No Known Activations