© 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. 11-RES-JB
    11. 24407
    Prev
    Next
    INDEX
    Explanations

    medical procedures or actions involving surgical tools

    oai_token-act-pair · gpt-3.5-turbo

    bizarre or graphic descriptions related to surgery or medical procedures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Clash
    -0.77
     Rally
    -0.71
     Parties
    -0.67
     Towns
    -0.66
     posters
    -0.65
     Earthquake
    -0.64
     rall
    -0.63
     resurg
    -0.61
     Disaster
    -0.61
     Shapiro
    -0.60
    POSITIVE LOGITS
     through
    1.09
     thru
    1.09
     protr
    1.05
     underneath
    1.04
     lodged
    1.02
     downwards
    1.02
    ifice
    0.99
     snug
    0.99
     into
    0.98
    through
    0.98
    Activations Density 0.223%

    No Known Activations