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. 23695
    Prev
    Next
    INDEX
    Explanations

    questions and phrases that seek clarification or specifics about a situation

    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
    243
    +0.13
    0.6%
    734
    +0.11
    0.5%
    210
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    243
    +0.13
    0.02
    542
    +0.11
    0.02
    589
    +0.11
    0.02
    Negative Logits
    ways
    -0.80
    eka
    -0.74
    cler
    -0.72
    gio
    -0.70
    way
    -0.67
    Pg
    -0.67
    bp
    -0.67
    rums
    -0.65
    uay
    -0.63
    oscope
    -0.63
    POSITIVE LOGITS
     happened
    0.71
     wrong
    0.68
    è¦
    0.66
    irements
    0.65
     programmed
    0.64
    èª
    0.64
     transpired
    0.62
    natureconservancy
    0.62
     thrust
    0.62
    ãĤ»
    0.62
    Activations Density 0.070%

    No Known Activations