© 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. 4424
    Prev
    Next
    INDEX
    Explanations

    descriptions of food and recipes

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

    punctuation and special characters

    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
     Tanzania
    -0.54
     Marriott
    -0.52
     Essex
    -0.49
     circuits
    -0.49
    ',"
    -0.48
     differed
    -0.48
     divisions
    -0.48
     divorced
    -0.46
     tc
    -0.45
     Jennings
    -0.45
    POSITIVE LOGITS
    HAHAHAHA
    0.95
    ï¸
    0.93
    Seriously
    0.90
    Yep
    0.88
    Wait
    0.87
    Congratulations
    0.87
    Thank
    0.86
    YES
    0.85
    Damn
    0.84
    Awesome
    0.84
    Activations Density 0.806%

    No Known Activations