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. 506
    Prev
    Next
    INDEX
    Explanations

    instances of the word "disclosure" or its related variations

    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
    441
    +0.13
    0.6%
    288
    +0.13
    0.6%
    195
    +0.13
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    441
    +0.13
    0.02
    195
    +0.13
    0.01
    424
    +0.13
    0.01
    Negative Logits
    ieval
    -0.82
    creation
    -0.79
    vic
    -0.79
    stad
    -0.69
    inal
    -0.68
    clock
    -0.68
    Äį
    -0.68
    jong
    -0.68
    create
    -0.66
    twitch
    -0.65
    POSITIVE LOGITS
     disclosure
    0.95
     disclosures
    0.94
     Disclosure
    0.88
     loopholes
    0.85
     disclosing
    0.85
     discl
    0.83
     disclose
    0.81
    saf
    0.75
     disclosed
    0.74
     filings
    0.74
    Activations Density 0.024%

    No Known Activations