© 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
    2. Joseph Bloom · Feature Splitting for GPT2-Small
    3. GPT2-Small
    4. Residual Feature Splitting 12288
    5. 8-RES_FS12288-JB
    6. 10566
    Prev
    Next
    INDEX
    Explanations

    legal terms and concepts

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs12288-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_12288
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    12,288
    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
    450
    +0.12
    0.5%
    500
    +0.10
    0.4%
    11
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    762
    +0.12
    0.08
    756
    +0.10
    -0.03
    450
    +0.09
    0.04
    Negative Logits
     timelines
    -0.90
     takeaway
    -0.85
     Spotlight
    -0.82
     timeline
    -0.82
     Timeline
    -0.77
     Danielle
    -0.76
    Baby
    -0.76
     UW
    -0.75
    osphere
    -0.74
    Wow
    -0.74
    POSITIVE LOGITS
    ,—
    1.56
     thence
    1.48
     negro
    1.22
     whence
    1.19
     hath
    1.17
     hitherto
    1.17
     labou
    1.15
     hereafter
    1.15
     chiefly
    1.13
     Edition
    1.12
    Activations Density 1.599%

    No Known Activations