© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 11-RES-JB
    6. 21580
    Prev
    Next
    INDEX
    Explanations

    punctuation marks within paired quotation marks

    oai_token-act-pair · gpt-3.5-turbo

    quotation marks and code-like syntax elements

    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
     Parish
    -0.85
     Emmy
    -0.82
     Patron
    -0.81
     Rhode
    -0.81
     Shepard
    -0.81
     Burnett
    -0.80
     Reich
    -0.79
     Versus
    -0.79
     TAMADRA
    -0.79
     Him
    -0.78
    POSITIVE LOGITS
    utils
    1.77
    plugins
    1.71
    tools
    1.70
    android
    1.68
    cli
    1.63
    runtime
    1.59
    client
    1.59
    plugin
    1.58
    apache
    1.58
    modules
    1.55
    Activations Density 0.146%

    No Known Activations