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. 11543
    Prev
    Next
    INDEX
    Explanations

    vague or intense descriptions or actions

    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
    481
    +0.27
    1.2%
    588
    +0.10
    0.4%
    638
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    429
    +0.27
    0.04
    638
    +0.10
    0.04
    669
    +0.10
    0.04
    Negative Logits
    iphate
    -0.78
    ifice
    -0.68
    obook
    -0.68
    ailable
    -0.65
    iggurat
    -0.65
    endment
    -0.65
    ãģ¾
    -0.64
    ilege
    -0.64
    ploma
    -0.62
    cko
    -0.62
    POSITIVE LOGITS
     observers
    0.92
    ly
    0.86
     fluctuations
    0.85
     Examples
    0.84
     examples
    0.82
     versions
    0.81
     copies
    0.81
    nesses
    0.80
     explanations
    0.79
     amounts
    0.79
    Activations Density 0.322%

    No Known Activations