© 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. 0-RES-JB
    11. 16335
    Prev
    Next
    INDEX
    Explanations

    mentions of the word "chemistry," particularly in the context of relationships or interactions

    oai_token-act-pair · gpt-3.5-turbo

    mentions of chemistry in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Nare
    -0.83
    ollow
    -0.75
    yip
    -0.74
    Il
    -0.69
    aunt
    -0.65
    Seg
    -0.65
    utt
    -0.64
     Vest
    -0.64
     haun
    -0.63
    Domain
    -0.62
    POSITIVE LOGITS
     chemistry
    4.16
     Chemistry
    2.92
     chemist
    1.90
    chem
    1.65
    ochemistry
    1.64
    Chem
    1.63
     biology
    1.54
     chem
    1.54
     physiology
    1.45
     physics
    1.41
    Activations Density 0.027%

    No Known Activations