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

    Neuronpedia

    Jacobian LensNEW
    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. 9-RES-JB
    11. 1917
    Prev
    Next
    INDEX
    Explanations

    associations between different variables (e.g., caffeine and cognitive decline, alcohol consumption and mortality, etc.)

    oai_token-act-pair · gpt-3.5-turbo

    correlations between various factors and health outcomes or cognitive functions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    cloth
    -0.78
     Vaugh
    -0.74
    poke
    -0.73
    DragonMagazine
    -0.71
    Rules
    -0.71
    =-=-
    -0.69
    uously
    -0.69
    assetsadobe
    -0.69
    adding
    -0.68
    Queue
    -0.68
    POSITIVE LOGITS
     susceptibility
    1.26
     likelihood
    1.17
     cognitive
    1.13
     mortality
    1.12
     propensity
    1.12
     cardiovascular
    1.11
     cognition
    1.07
     incidence
    1.05
     lifespan
    1.01
     longevity
    1.00
    Activations Density 0.289%

    No Known Activations