© 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 EvalsExportsinterp-engineNEWAPI 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. 23451
    Prev
    Next
    INDEX
    Explanations

    scientific studies and their findings related to various health and lifestyle factors

    oai_token-act-pair · gpt-3.5-turbo

    references to the impact of substances on health outcomes

    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
    stros
    -0.80
     Profit
    -0.77
    phies
    -0.68
    Crew
    -0.67
    çīĪ
    -0.66
    Assembly
    -0.65
     converter
    -0.65
     Paradise
    -0.65
    oche
    -0.65
     myster
    -0.64
    POSITIVE LOGITS
     interventions
    1.08
     exposure
    1.04
     induces
    0.96
     stimulates
    0.94
     influences
    0.91
     inhibits
    0.88
     exposures
    0.88
     activates
    0.88
     supplementation
    0.87
     intervention
    0.87
    Activations Density 0.512%

    No Known Activations