© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 4-RES-JB
    6. 4529
    Prev
    Next
    INDEX
    Explanations

    words related to chemical reactions and compounds

    oai_token-act-pair · gpt-3.5-turbo

    terms related to chemical reactions and their effects

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

    No Comments

    Negative Logits
    uckland
    -0.90
    cffffcc
    -0.79
    isphere
    -0.77
     Ranked
    -0.74
    HUD
    -0.72
    Minnesota
    -0.71
    panic
    -0.70
    Privacy
    -0.68
    yright
    -0.68
    kids
    -0.67
    POSITIVE LOGITS
     coating
    1.07
     oxid
    1.07
    oxide
    1.05
     nanop
    1.04
     oxide
    1.03
     substr
    1.03
     metals
    1.02
     chemically
    1.01
     powd
    1.00
     molecules
    1.00
    Activations Density 0.199%

    No Known Activations