© 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. 6-RES-JB
    11. 17388
    Prev
    Next
    INDEX
    Explanations

    medical conditions and treatments such as atherosclerosis, vasopressin, cerebrovascular events, and surgeries like gastrectomy

    oai_token-act-pair · gpt-3.5-turbo

    terms related to medical research and conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Grounds
    -0.78
     Monthly
    -0.76
     Fool
    -0.75
     Purg
    -0.75
    AU
    -0.74
    Rules
    -0.72
    Money
    -0.72
     Rules
    -0.71
     Yard
    -0.70
    Beast
    -0.70
    POSITIVE LOGITS
    emia
    1.27
    ogenic
    1.11
    emic
    1.04
    osis
    1.04
    olesterol
    1.02
    idine
    1.02
    rosis
    1.00
    cular
    1.00
    oxin
    0.99
     toxin
    0.98
    Activations Density 0.194%

    No Known Activations