© 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. 12-RES-JB
    11. 3497
    Prev
    Next
    INDEX
    Explanations

    proper nouns related to political figures or entities

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot

    dates and locations in news articles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 12-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.hook_resid_post
    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_post
    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
     tiss
    -1.34
     eleph
    -1.29
     oun
    -1.26
     ende
    -1.23
     confir
    -1.22
     obser
    -1.22
    sembly
    -1.19
     exting
    -1.19
     occas
    -1.14
     encount
    -1.11
    POSITIVE LOGITS
    FILE
    0.91
    Hand
    0.81
    Sl
    0.74
    ($
    0.72
    XT
    0.70
    Veh
    0.68
    People
    0.68
    Standard
    0.66
    Digital
    0.64
    Weak
    0.64
    Activations Density 0.033%

    No Known Activations