© 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. 11-RES-JB
    11. 20639
    Prev
    Next
    INDEX
    Explanations

    chemical compounds and substances

    oai_token-act-pair · gpt-3.5-turbo

    terms related to chemicals and substances impacting health and the environment

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    hani
    -0.88
    anmar
    -0.83
    ruby
    -0.79
    rians
    -0.73
    olitan
    -0.73
    luaj
    -0.73
    inosaur
    -0.72
    Solar
    -0.72
     Afric
    -0.71
    Downloadha
    -0.69
    POSITIVE LOGITS
     intoxication
    1.38
     poisoning
    1.35
     concentrations
    1.34
     toxicity
    1.32
     exposure
    1.32
     ingestion
    1.27
     deficiency
    1.27
     levels
    1.26
     consumption
    1.26
     secretion
    1.21
    Activations Density 0.191%

    No Known Activations