Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & 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. 830
    Prev
    Next
    INDEX
    Explanations

    phrases related to antibiotics and antibiotic resistance

    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
    +0.13
    0.6%
    481
    +0.13
    0.6%
    385
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.13
    0.02
    516
    +0.13
    0.01
    189
    +0.11
    0.01
    Negative Logits
    jri
    -0.77
    wagen
    -0.76
    ulhu
    -0.73
    DEM
    -0.70
     Lumpur
    -0.69
     largeDownload
    -0.69
    ITNESS
    -0.68
    foundland
    -0.67
    chool
    -0.67
    ĸļ
    -0.67
    POSITIVE LOGITS
    illin
    1.08
    icrobial
    0.98
     treatment
    0.93
     treatments
    0.87
     medication
    0.86
     prescription
    0.86
     prescribing
    0.85
     antibiotics
    0.85
     prescriptions
    0.83
     resistant
    0.82
    Activations Density 0.024%

    No Known Activations