© 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. 10-RES-JB
    11. 20519
    Prev
    Next
    INDEX
    Explanations

    medical conditions and treatments, including bodily afflictions and procedures

    oai_token-act-pair · gpt-3.5-turbo

    terms associated with health conditions and bodily injuries

    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
    soDeliveryDate
    -1.02
    htaking
    -0.74
    agall
    -0.73
    isSpecialOrderable
    -0.72
    arcity
    -0.72
    href
    -0.69
    displayText
    -0.69
    Trend
    -0.68
    stall
    -0.68
    rw
    -0.68
    POSITIVE LOGITS
     lungs
    1.74
     kidneys
    1.61
     muscles
    1.58
     bloodstream
    1.54
     arteries
    1.53
     digestive
    1.51
     organs
    1.50
     liver
    1.49
     tissues
    1.49
     body
    1.49
    Activations Density 0.173%

    No Known Activations