© 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 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. 7683
    Prev
    Next
    INDEX
    Explanations

    poetry-related terms and themes

    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
    401
    +0.11
    0.5%
    7
    +0.11
    0.5%
    447
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    401
    +0.11
    0.02
    575
    +0.11
    0.02
    11
    +0.10
    0.01
    Negative Logits
     clamp
    -0.74
    adjusted
    -0.70
    erate
    -0.70
    zinski
    -0.70
    rals
    -0.68
     WATCHED
    -0.66
    rollers
    -0.65
     Lumpur
    -0.65
    tch
    -0.65
    ticket
    -0.64
    POSITIVE LOGITS
     laureate
    1.34
     poems
    1.34
     poem
    1.29
     poetry
    1.27
     poets
    1.10
     poet
    1.07
     poetic
    0.97
    writer
    0.96
     lyrics
    0.92
    writing
    0.91
    Activations Density 0.045%

    No Known Activations