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. 11796
    Prev
    Next
    INDEX
    Explanations

    mentions of the Veterans Affairs (VA) department and related terms

    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
    288
    +0.16
    0.7%
    659
    +0.13
    0.6%
    270
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    146
    +0.16
    0.01
    288
    +0.13
    0.01
    444
    +0.12
    0.01
    Negative Logits
    pins
    -0.93
    lihood
    -0.83
     Ãĸ
    -0.78
    ãĤ¦ãĤ¹
    -0.76
    gered
    -0.75
    notations
    -0.75
    ness
    -0.73
    ãĥł
    -0.73
    hower
    -0.71
    lio
    -0.71
    POSITIVE LOGITS
    ULT
    0.87
    MC
    0.82
    ULTS
    0.79
    UGH
    0.78
     Accountability
    0.77
     Medical
    0.77
    IL
    0.75
     hospital
    0.74
    ACC
    0.73
     Pharmaceutical
    0.71
    Activations Density 0.019%

    No Known Activations