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. 23710
    Prev
    Next
    INDEX
    Explanations

    words or phrases that signify particular entities, such as brands, locations, or notable organizations

    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
    480
    +0.49
    2.6%
    266
    +0.13
    0.6%
    87
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    232
    +0.49
    0.08
    480
    +0.13
    0.02
    266
    +0.10
    0.06
    Negative Logits
    theless
    -0.71
     referen
    -0.67
     describ
    -0.63
     acknow
    -0.62
    anwhile
    -0.60
    é¾įå¥ij士
    -0.60
     normalized
    -0.59
     nomine
    -0.59
     pleas
    -0.58
     subscribed
    -0.57
    POSITIVE LOGITS
    itars
    0.84
    eworks
    0.81
    astery
    0.81
    ifles
    0.80
    uctions
    0.75
    istries
    0.75
    pit
    0.75
    isan
    0.75
    tones
    0.74
     Festival
    0.71
    Activations Density 0.363%

    No Known Activations