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. 609
    Prev
    Next
    INDEX
    Explanations

    phrases related to legal matters or legislation

    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
    362
    +0.14
    0.6%
    371
    +0.12
    0.5%
    314
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    371
    +0.14
    0.08
    362
    +0.12
    0.07
    172
    +0.12
    0.06
    Negative Logits
    FTWARE
    -0.72
    lda
    -0.68
    Pac
    -0.67
    Ops
    -0.64
    NESS
    -0.64
    glass
    -0.63
    ption
    -0.62
    DonaldTrump
    -0.62
    fill
    -0.61
    Video
    -0.61
    POSITIVE LOGITS
     least
    1.25
    onement
    1.01
     intervals
    0.97
    yp
    0.90
     whim
    0.87
     halftime
    0.87
    abase
    0.86
     times
    0.85
     home
    0.82
     variance
    0.82
    Activations Density 0.184%

    No Known Activations