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. 23789
    Prev
    Next
    INDEX
    Explanations

    various forms of reference or descriptors related to functionality, like those associated with code, health, and corporate contexts

    oai_token-act-pair · gpt-4o-miniTriggered 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
    +0.17
    0.8%
    314
    +0.12
    0.6%
    564
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.17
    0.08
    575
    +0.12
    0.07
    40
    +0.11
    0.05
    Negative Logits
    ussions
    -0.67
    ones
    -0.67
    nant
    -0.62
    ainers
    -0.61
    gur
    -0.59
    racuse
    -0.59
    rarily
    -0.59
    someone
    -0.58
    rogens
    -0.58
     Highlander
    -0.58
    POSITIVE LOGITS
    eworld
    0.79
    mma
    0.73
     selves
    0.73
    ĸļ
    0.69
    âĺ
    0.69
    ultimate
    0.69
    stretched
    0.62
     closest
    0.62
    ouf
    0.61
     destiny
    0.61
    Activations Density 0.485%

    No Known Activations