Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Feature Splitting for GPT2-Small
    3. GPT2-Small
    4. Residual Feature Splitting 24576
    5. 8-RES_FS24576-JB
    6. 23313
    Prev
    Next
    INDEX
    Explanations

    various forms of digital content and educational material

    oai_token-act-pair · gpt-4o-miniTriggered 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
    175
    +0.14
    0.6%
    496
    +0.11
    0.5%
    578
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    175
    +0.14
    0.04
    739
    +0.11
    0.03
    326
    +0.11
    0.04
    Negative Logits
    oÄŁ
    -0.67
    alysis
    -0.64
    ously
    -0.64
    lier
    -0.64
    ×Ķ
    -0.61
     maneuvers
    -0.61
    SpaceEngineers
    -0.60
    itiz
    -0.59
    times
    -0.59
    tif
    -0.58
    POSITIVE LOGITS
    ource
    1.30
    ystem
    1.20
    peed
    1.19
    etter
    1.11
    hip
    1.11
    mith
    1.10
    hift
    1.10
    heet
    1.08
    cript
    1.08
    ettings
    1.08
    Activations Density 0.200%

    No Known Activations