© 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. 8913
    Prev
    Next
    INDEX
    Explanations

    information related to literary works or books

    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
    481
    +0.20
    0.9%
    447
    +0.11
    0.5%
    175
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    175
    +0.20
    0.03
    396
    +0.11
    0.03
    710
    +0.10
    0.03
    Negative Logits
     refuel
    -0.83
     GoPro
    -0.81
     Qualcomm
    -0.80
     Razer
    -0.79
    twitch
    -0.78
     Lyft
    -0.77
     valve
    -0.74
    apesh
    -0.73
     thrott
    -0.71
    merga
    -0.70
    POSITIVE LOGITS
     essays
    1.58
     manuscript
    1.54
     manuscripts
    1.52
     poems
    1.46
     chapters
    1.35
     autobi
    1.34
     books
    1.33
     passages
    1.31
     excerpts
    1.30
     memoir
    1.28
    Activations Density 0.642%

    No Known Activations