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. 23636
    Prev
    Next
    INDEX
    Explanations

    instances and references to the term "mast" in various 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
    23
    +0.12
    0.5%
    216
    +0.11
    0.5%
    195
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.12
    0.02
    690
    +0.11
    0.01
    325
    +0.11
    0.01
    Negative Logits
    ppo
    -0.81
    ITED
    -0.74
    mble
    -0.72
    lda
    -0.71
    \\\\\\\\
    -0.65
     Witness
    -0.63
    bre
    -0.62
     Libre
    -0.62
     Borders
    -0.61
    guyen
    -0.60
    POSITIVE LOGITS
    erers
    0.97
    ific
    0.94
    hetically
    0.94
    odon
    0.92
    erer
    0.90
    ectomy
    0.89
    ication
    0.83
    roxy
    0.82
    urb
    0.82
    rogens
    0.82
    Activations Density 0.035%

    No Known Activations