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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 6-RES-JB
    6. 19916
    Prev
    Next
    INDEX
    Explanations

    statistics-related terms and measurements, possibly related to medical research or epidemiology

    oai_token-act-pair · gpt-3.5-turbo

    terminology related to mortality statistics and risk assessment

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    oil
    -0.88
    aunder
    -0.82
    ouver
    -0.81
     embr
    -0.81
    assetsadobe
    -0.80
    Bit
    -0.77
    urrency
    -0.75
    atron
    -0.75
     horizont
    -0.74
    Artist
    -0.73
    POSITIVE LOGITS
     clinical
    1.09
     maternal
    1.08
     cohort
    1.06
     clinically
    1.03
     cardiovascular
    1.03
     psychiatric
    1.01
     morbid
    1.01
     obesity
    1.01
     epidem
    1.00
     Clinical
    0.99
    Activations Density 0.464%

    No Known Activations