© 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. 22458
    Prev
    Next
    INDEX
    Explanations

    names or titles containing the prefix "La" followed by a common English word

    oai_token-act-pair · gpt-3.5-turbo

    references to specific individuals or characters, particularly those with names starting with "La."

    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
    rawdownloadcloneembedreportprint
    -0.72
    é¾įå¥ij士
    -0.65
    PORT
    -0.62
     Osw
    -0.61
    SHIP
    -0.55
     Raz
    -0.55
     hig
    -0.54
     Faust
    -0.54
     Scandinav
    -0.54
     è£ıç
    -0.54
    POSITIVE LOGITS
    helle
    0.95
    alle
    0.91
    otta
    0.87
    onge
    0.84
    olla
    0.84
    igne
    0.79
    uliffe
    0.79
    agne
    0.78
    elle
    0.77
    arge
    0.73
    Activations Density 0.048%

    No Known Activations