© 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 12288
    9. 8-RES_FS12288-JB
    11. 9594
    Prev
    Next
    INDEX
    Explanations

    teasers and announcements related to Marvel comics and releases

    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
    233
    +0.12
    0.6%
    460
    +0.10
    0.5%
    641
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    460
    +0.12
    0.05
    274
    +0.10
    0.05
    427
    +0.09
    0.04
    Negative Logits
    tein
    -0.92
    bard
    -0.81
    istries
    -0.80
    insured
    -0.79
    ictionary
    -0.75
    anasia
    -0.73
    zanne
    -0.72
    isine
    -0.71
    illegal
    -0.69
    itute
    -0.69
    POSITIVE LOGITS
     teaser
    1.35
     unveil
    1.16
     trailer
    1.12
     previews
    1.11
     trailers
    1.09
     unveiling
    1.06
     announcing
    1.04
     specs
    1.03
     preview
    1.03
     teased
    1.02
    Activations Density 0.569%

    No Known Activations