© 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. 11-RES-JB
    11. 3373
    Prev
    Next
    INDEX
    Explanations

    various chemical compounds and their related terms

    oai_token-act-pair · gpt-3.5-turbo

    chemical names and related compounds

    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
     Stra
    -0.72
     Revel
    -0.72
     Gunn
    -0.70
     Panda
    -0.69
     quirks
    -0.67
     navigating
    -0.66
     Space
    -0.66
     Crowd
    -0.65
     gaping
    -0.64
     Replay
    -0.64
    POSITIVE LOGITS
    idine
    1.68
    amide
    1.61
    oxide
    1.56
    aldehyde
    1.52
    anol
    1.45
    amine
    1.40
    oxin
    1.39
    ethy
    1.37
    ethyl
    1.37
    ophen
    1.35
    Activations Density 0.131%

    No Known Activations