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. 1188
    Prev
    Next
    INDEX
    Explanations

    names of countries

    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
    442
    +0.10
    0.4%
    194
    +0.09
    0.4%
    563
    +0.08
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    232
    +0.10
    0.05
    284
    +0.09
    0.05
    659
    +0.08
    0.05
    Negative Logits
    etheless
    -0.65
    BuyableInstoreAndOnline
    -0.64
    eatures
    -0.64
    ãĥİ
    -0.62
    é¾įå¥ij士
    -0.60
    wat
    -0.60
    ylene
    -0.59
    PDATE
    -0.58
    acebook
    -0.58
     aggregation
    -0.56
    POSITIVE LOGITS
    ère
    0.94
    arson
    0.89
     Parish
    0.81
    ffe
    0.77
    igne
    0.77
    iere
    0.74
    iffe
    0.73
    heny
    0.72
    ese
    0.71
     Dame
    0.71
    Activations Density 0.158%

    No Known Activations