© 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. 9-RES-JB
    11. 4255
    Prev
    Next
    INDEX
    Explanations

    words related to chemistry and biology including chemical reactions, substances, and bodily functions

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     categ
    -0.71
     Partnership
    -0.68
     Advent
    -0.68
     endorsement
    -0.66
     Creed
    -0.65
     Lithuan
    -0.65
     reservation
    -0.64
     tenure
    -0.64
     Improvement
    -0.64
     Wanted
    -0.64
    POSITIVE LOGITS
     stimulates
    1.07
     contam
    1.05
     contamin
    1.02
     then
    1.02
     causes
    1.01
     eventually
    0.97
     wre
    0.95
     deposited
    0.95
     destroys
    0.95
     emits
    0.94
    Activations Density 0.539%

    No Known Activations