© 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. 7829
    Prev
    Next
    INDEX
    Explanations

    short URLs

    oai_token-act-pair · gpt-3.5-turbo

    web addresses, particularly those ending in "ly" and common domain extensions

    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
    -0.62
    alian
    -0.59
     pupils
    -0.58
     whichever
    -0.54
    ò
    -0.54
     oun
    -0.54
    igans
    -0.53
     helicop
    -0.52
     exting
    -0.52
     Gott
    -0.52
    POSITIVE LOGITS
    /-
    0.95
    /+
    0.87
    /?
    0.85
    /
    0.84
    /_
    0.83
    /
    0.79
    img
    0.78
    /*
    0.75
    //
    0.73
    lihood
    0.72
    Activations Density 0.014%

    No Known Activations