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. 21878
    Prev
    Next
    INDEX
    Explanations

    phrases related to mental health

    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
    762
    +0.14
    0.7%
    508
    +0.12
    0.6%
    447
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    508
    +0.14
    0.02
    762
    +0.12
    0.02
    288
    +0.12
    0.02
    Negative Logits
    SN
    -0.88
    yss
    -0.77
    rawdownloadcloneembedreportprint
    -0.73
    iPhone
    -0.70
    Recipe
    -0.70
    yip
    -0.69
    umo
    -0.69
    issan
    -0.69
    rily
    -0.68
    Solar
    -0.66
    POSITIVE LOGITS
     counseling
    1.07
     disorders
    1.06
     counselors
    1.00
     professionals
    0.99
     diagnoses
    0.99
     treatment
    0.97
     rehabilitation
    0.92
    ilitating
    0.91
     care
    0.90
     counselling
    0.90
    Activations Density 0.047%

    No Known Activations