© 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. 2-RES-JB
    11. 9518
    Prev
    Next
    INDEX
    Explanations

    mentions of chemistry and chemical-related terms

    oai_token-act-pair · gpt-3.5-turbo

    references to chemistry and its various applications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    gotten
    -0.75
    agle
    -0.72
    ittle
    -0.70
    cise
    -0.70
    early
    -0.70
    fty
    -0.69
    clusive
    -0.66
    por
    -0.66
    grim
    -0.65
    avement
    -0.63
    POSITIVE LOGITS
     chemistry
    1.43
    istry
    1.06
     Chemistry
    0.97
     chemist
    0.95
    Chem
    0.88
    odynamics
    0.86
    chem
    0.85
    ochemistry
    0.78
    istries
    0.78
     potions
    0.77
    Activations Density 0.011%

    No Known Activations