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. 23321
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate change, growth, or progress in various contexts

    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
    417
    +0.11
    0.5%
    413
    +0.10
    0.5%
    701
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    417
    +0.11
    0.04
    402
    +0.10
    0.04
    324
    +0.10
    0.04
    Negative Logits
     Cups
    -0.70
    pages
    -0.66
    asus
    -0.64
    rooms
    -0.63
    liam
    -0.61
    ovies
    -0.61
     Empires
    -0.59
     headlines
    -0.59
     Fixed
    -0.57
    ancies
    -0.57
    POSITIVE LOGITS
     reminder
    0.85
    iator
    0.84
     homage
    0.81
     thereof
    0.81
     unto
    0.81
     reflection
    0.77
     testament
    0.77
    lude
    0.76
     culmination
    0.75
     reim
    0.75
    Activations Density 0.188%

    No Known Activations