© 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. 10-RES-JB
    11. 12072
    Prev
    Next
    INDEX
    Explanations

    words related to chemical compounds or elements

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ockets
    -0.74
    corn
    -0.71
    abet
    -0.66
    ploma
    -0.64
    ı
    -0.64
    à©
    -0.63
    ®
    -0.63
    Bird
    -0.62
     Gunn
    -0.62
    Ŀ
    -0.62
    POSITIVE LOGITS
    ioned
    0.78
    adium
    0.77
    iliary
    0.75
    inct
    0.71
    cules
    0.70
     Afric
    0.68
     occupancy
    0.68
    IFIED
    0.68
    es
    0.66
     annex
    0.66
    Activations Density 0.085%

    No Known Activations