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. 19251
    Prev
    Next
    INDEX
    Explanations

    large financial figures or amounts, such as prices and costs

    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
    759
    +0.12
    0.5%
    545
    +0.09
    0.4%
    373
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    495
    +0.12
    0.04
    165
    +0.09
    0.03
    352
    +0.09
    0.04
    Negative Logits
    hess
    -0.78
    gravity
    -0.74
    quickShipAvailable
    -0.69
    selection
    -0.68
    sharp
    -0.67
    Ctrl
    -0.67
     Retro
    -0.67
    Sty
    -0.66
    girls
    -0.66
    bro
    -0.66
    POSITIVE LOGITS
     million
    1.25
     billion
    1.10
     MILL
    0.98
     Million
    0.90
    million
    0.89
    -$
    0.86
     Billion
    0.84
     crore
    0.83
    illion
    0.81
    Ń·
    0.78
    Activations Density 0.078%

    No Known Activations