© 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. 11-RES-JB
    11. 13544
    Prev
    Next
    INDEX
    Explanations

    names of individuals along with their professions

    oai_token-act-pair · gpt-3.5-turbo

    proper nouns, particularly names of individuals and their titles or roles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     physically
    -0.62
     processed
    -0.57
     technically
    -0.56
     partying
    -0.56
     servicing
    -0.56
     safely
    -0.54
     resultant
    -0.54
     transitioning
    -0.53
     matched
    -0.53
     captcha
    -0.53
    POSITIVE LOGITS
     Shapiro
    0.95
     Friedman
    0.94
     Feldman
    0.91
     Schwartz
    0.91
     Levin
    0.90
     Levine
    0.90
     Katz
    0.90
     Rosenthal
    0.87
     Carlson
    0.86
     Cohen
    0.86
    Activations Density 0.326%

    No Known Activations