© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 10315
    Prev
    Next
    INDEX
    Explanations

    technology-related terms like "stereo-vision projector" and "high-resolution cameras."

    oai_token-act-pair · gpt-3.5-turbo

    terms related to visual technology and imaging

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
     Rebell
    -0.98
     Nug
    -0.90
     Pork
    -0.82
     Beef
    -0.82
     Briggs
    -0.80
     Commit
    -0.78
    icio
    -0.78
    Fed
    -0.77
     Starter
    -0.74
     Heist
    -0.73
    POSITIVE LOGITS
     glare
    1.59
     infrared
    1.58
     ultraviolet
    1.47
     illumination
    1.40
     visual
    1.36
     illuminated
    1.35
     wavelengths
    1.35
     visibility
    1.32
     telescopes
    1.32
     brightness
    1.30
    Activations Density 0.882%

    No Known Activations