© 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 · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 10-RES-JB
    6. 10292
    Prev
    Next
    INDEX
    Explanations

    words related to therapeutic or medical treatments

    oai_token-act-pair · gpt-3.5-turbo

    references to therapeutic concepts and treatments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     duty
    -0.67
     Elk
    -0.65
     seeded
    -0.64
     Starr
    -0.63
    ELS
    -0.63
     Mayer
    -0.63
     rooted
    -0.62
     Blow
    -0.59
     Unch
    -0.59
     Rate
    -0.59
    POSITIVE LOGITS
    apist
    1.56
    apy
    1.33
    mop
    1.21
    ape
    1.16
    most
    1.15
    mal
    1.11
    anos
    1.09
    mins
    1.06
    mid
    1.05
    mite
    1.03
    Activations Density 0.028%

    No Known Activations