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. 23853
    Prev
    Next
    INDEX
    Explanations

    numerical data and statistics related to health and environmental impacts

    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
    260
    +0.10
    0.5%
    223
    +0.10
    0.5%
    162
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    260
    +0.10
    0.10
    223
    +0.10
    0.09
    310
    +0.09
    0.08
    Negative Logits
     Played
    -0.67
    evin
    -0.66
     prelim
    -0.64
     jerk
    -0.63
     deed
    -0.60
    ↵Âł
    -0.60
    nesota
    -0.59
     defendant
    -0.59
     wording
    -0.58
     distance
    -0.58
    POSITIVE LOGITS
     million
    1.36
     billion
    1.22
    %
    1.17
     lakh
    1.16
     percent
    1.13
    million
    1.13
     trillion
    1.11
    %"
    1.09
     crore
    1.07
    %-
    1.05
    Activations Density 0.247%

    No Known Activations