© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 17433
    Prev
    Next
    INDEX
    Explanations

    medical and health-related terms, including words related to medical conditions, treatments, and studies

    oai_token-act-pair · gpt-3.5-turbo

    evidence related to cognitive performance and health outcomes

    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
     extradition
    -0.69
     Travels
    -0.68
     vend
    -0.67
     assures
    -0.66
    soDeliveryDate
    -0.66
    rastructure
    -0.65
     extrad
    -0.62
     Throne
    -0.62
     commod
    -0.62
     lays
    -0.62
    POSITIVE LOGITS
     (âĪĴ
    1.23
     âĪ¼
    1.07
     placebo
    1.02
     statistically
    1.01
     decreased
    0.97
    RESULTS
    0.95
    β
    0.91
     âĪĴ
    0.89
     âī¥
    0.89
     ±
    0.86
    Activations Density 0.741%

    No Known Activations