© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Joseph Bloom · Feature Splitting for GPT2-Small
    3. GPT2-Small
    4. Residual Feature Splitting 24576
    5. 8-RES_FS24576-JB
    6. 8088
    Prev
    Next
    INDEX
    Explanations

    medical terminology related to end-of-life care and terminally ill patients

    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
    77
    +0.12
    0.6%
    114
    +0.12
    0.5%
    476
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    114
    +0.12
    0.01
    288
    +0.12
    0.01
    147
    +0.11
    0.01
    Negative Logits
    rouse
    -0.68
    hari
    -0.67
    htaking
    -0.67
    itsch
    -0.65
     stead
    -0.64
    encers
    -0.63
    rious
    -0.63
    artisan
    -0.61
    rahim
    -0.61
    puff
    -0.61
    POSITIVE LOGITS
     termin
    0.91
     termination
    0.84
    angering
    0.78
     parole
    0.78
     pregnancies
    0.75
    termin
    0.74
     terminated
    0.74
    locks
    0.73
    atos
    0.71
    angered
    0.70
    Activations Density 0.018%

    No Known Activations