© 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. 3-RES-JB
    11. 18079
    Prev
    Next
    INDEX
    Explanations

    dates and URLs related to blog posts, news stories, and articles

    oai_token-act-pair · gpt-3.5-turbo

    URLs or web links, particularly in a news context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     apologised
    -0.72
     oun
    -0.71
     clin
    -0.70
     mate
    -0.67
     concede
    -0.66
     imperson
    -0.66
     creep
    -0.65
    erville
    -0.64
     wards
    -0.64
     apologise
    -0.63
    POSITIVE LOGITS
    uploads
    1.09
    etc
    1.07
    index
    1.07
    photos
    1.06
    Accessory
    1.04
    archives
    1.03
    pol
    1.03
    upload
    1.00
    pmwiki
    0.98
    sites
    0.98
    Activations Density 0.046%

    No Known Activations