© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 20631
    Prev
    Next
    INDEX
    Explanations

    quotations within text

    oai_token-act-pair · gpt-3.5-turbo

    quotation marks and dialogue

    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
     eleph
    -0.85
     quir
    -0.83
     avatar
    -0.78
     occas
    -0.77
     pumped
    -0.77
     squid
    -0.76
     stra
    -0.76
     plaster
    -0.75
     subur
    -0.75
     booked
    -0.75
    POSITIVE LOGITS
    Let
    1.59
    Tonight
    1.58
    Look
    1.57
    If
    1.56
    Everybody
    1.55
    Clearly
    1.55
    I
    1.54
    Enough
    1.54
    Nobody
    1.54
    Absolutely
    1.53
    Activations Density 0.137%

    No Known Activations