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. 11703
    Prev
    Next
    INDEX
    Explanations

    the names of various colleges and universities

    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
    359
    +0.10
    0.5%
    62
    +0.10
    0.4%
    15
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    659
    +0.10
    0.05
    232
    +0.10
    0.04
    299
    +0.10
    0.04
    Negative Logits
    BILITIES
    -1.04
    BILITY
    -0.78
    vironment
    -0.75
    ĻĤ
    -0.70
    Applic
    -0.66
     pes
    -0.64
    ãĥĩ
    -0.63
    20439
    -0.63
    FontSize
    -0.62
     Tos
    -0.61
    POSITIVE LOGITS
    schild
    0.78
    nir
    0.76
    arson
    0.72
    etus
    0.69
    api
    0.67
    arma
    0.66
    lich
    0.66
    ahime
    0.65
    angs
    0.64
    igans
    0.64
    Activations Density 0.114%

    No Known Activations