© 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. 20428
    Prev
    Next
    INDEX
    Explanations

    hyphenated numerical values indicating a decrease

    oai_token-act-pair · gpt-3.5-turbo

    document structures or formatting 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
     Cassidy
    -0.73
     turbulence
    -0.67
     RTX
    -0.66
     scenery
    -0.66
     STA
    -0.65
     NV
    -0.63
     NP
    -0.62
    ãĤ¯
    -0.62
     DRAG
    -0.62
     Klu
    -0.62
    POSITIVE LOGITS
    eight
    2.12
    five
    2.11
    nine
    2.08
    seven
    2.07
    six
    2.06
    three
    2.00
    four
    2.00
    two
    1.98
    one
    1.67
    fifth
    1.56
    Activations Density 0.028%

    No Known Activations