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 24576
    5. 8-RES_FS24576-JB
    6. 11369
    Prev
    Next
    INDEX
    Explanations

    countries or nationalities

    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
    542
    +0.11
    0.5%
    288
    +0.11
    0.5%
    616
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    65
    +0.11
    0.07
    752
    +0.11
    0.07
    57
    +0.11
    0.06
    Negative Logits
    eus
    -0.82
    hots
    -0.80
    ocrates
    -0.79
    arella
    -0.78
    Downloadha
    -0.78
    paio
    -0.76
    redd
    -0.76
    bg
    -0.75
    vg
    -0.74
    possibly
    -0.74
    POSITIVE LOGITS
     populace
    1.22
     equivalent
    1.17
     electorate
    1.14
     psyche
    1.13
     economy
    1.13
     countryside
    1.09
     presidency
    1.07
     Republic
    1.06
     Federation
    1.05
     Revolution
    1.04
    Activations Density 0.184%

    No Known Activations