© 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. 8588
    Prev
    Next
    INDEX
    Explanations

    references to scientific studies and health-related topics

    oai_token-act-pair · gpt-3.5-turbo

    references to studies and statistical findings related to health

    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
     evict
    -0.82
     blat
    -0.74
    eve
    -0.71
     Optimus
    -0.69
     actionGroup
    -0.67
     ruth
    -0.66
     hacker
    -0.66
     secession
    -0.66
     traitor
    -0.66
     exile
    -0.66
    POSITIVE LOGITS
    Study
    1.42
     studies
    1.41
    Studies
    1.39
     study
    1.37
    Researchers
    1.37
     Pediatrics
    1.35
     researchers
    1.34
    study
    1.32
     Physicians
    1.28
     Lancet
    1.26
    Activations Density 0.572%

    No Known Activations