© 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
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 0-RES-JB
    11. 5279
    Prev
    Next
    INDEX
    Explanations

    medical procedures

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "procedure" and related terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    friends
    -0.88
    illions
    -0.78
    asters
    -0.75
    idas
    -0.74
    osponsors
    -0.74
    ooks
    -0.72
    stories
    -0.70
    monds
    -0.70
    idges
    -0.69
    hett
    -0.68
    POSITIVE LOGITS
     procedure
    3.69
     Procedure
    2.64
     procedures
    1.81
     process
    1.73
     protocol
    1.56
     technique
    1.55
     Procedures
    1.55
     operation
    1.37
     method
    1.37
     mechanism
    1.32
    Activations Density 0.019%

    No Known Activations