© 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. 11371
    Prev
    Next
    INDEX
    Explanations

    phrases related to legal or political decisions

    oai_token-act-pair · gpt-3.5-turbo

    statements related to legal and political rulings

    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
     researching
    -0.68
    angler
    -0.67
     frequent
    -0.61
     util
    -0.59
     frequ
    -0.59
    aimon
    -0.59
     hybrids
    -0.59
    arthed
    -0.58
    limits
    -0.58
     Loft
    -0.57
    POSITIVE LOGITS
    Congratulations
    1.21
     Congratulations
    1.13
     congratulations
    1.08
     vind
    1.04
     victory
    0.99
     disappointed
    0.95
     congratulate
    0.93
     congr
    0.92
    âĢİ
    0.91
     losers
    0.89
    Activations Density 1.033%

    No Known Activations