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 3072
    5. 8-RES_FS3072-JB
    6. 864
    Prev
    Next
    INDEX
    Explanations

    words related to legal issues or conflicts

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs3072-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_3072
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    3,072
    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
    497
    +0.13
    0.6%
    373
    +0.13
    0.6%
    205
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    284
    +0.13
    0.09
    659
    +0.13
    0.09
    373
    +0.10
    -0.04
    Negative Logits
    itiveness
    -0.74
    iliary
    -0.67
    glers
    -0.66
    retty
    -0.65
    grain
    -0.63
    gerald
    -0.61
    lde
    -0.60
    mercial
    -0.59
     magnification
    -0.59
    bley
    -0.58
    POSITIVE LOGITS
    azeera
    1.06
    querque
    0.88
    aeda
    0.85
    aida
    0.79
    Qaeda
    0.77
    abet
    0.77
    ieri
    0.76
    addin
    0.74
    arez
    0.73
    ãĥķãĤ©
    0.73
    Activations Density 1.047%

    No Known Activations