Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Feature Splitting for GPT2-Small
    3. GPT2-Small
    4. Residual Feature Splitting 768
    5. 8-RES_FS768-JB
    6. 624
    Prev
    Next
    INDEX
    Explanations

    sports-related terms and information

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs768-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_768
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    768
    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
    146
    +0.10
    0.5%
    381
    +0.09
    0.4%
    341
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    362
    +0.10
    0.18
    393
    +0.09
    0.17
    146
    +0.09
    0.08
    Negative Logits
    arella
    -0.75
    loads
    -0.69
    eus
    -0.65
    etsk
    -0.65
     loopholes
    -0.65
     tears
    -0.64
    plets
    -0.60
     cheers
    -0.60
     caveats
    -0.59
    Of
    -0.58
    POSITIVE LOGITS
     nutshell
    0.75
     millennium
    0.72
    thood
    0.71
     Ancients
    0.70
     Confederacy
    0.69
     Invention
    0.68
     universe
    0.66
     respective
    0.62
     utmost
    0.62
     century
    0.61
    Activations Density 5.108%

    No Known Activations