© 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. 8-RES-JB
    11. 19258
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate importance or relevance

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating the presence of records or documentation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    west
    -0.73
    iHUD
    -0.72
    \\\\\\\\
    -0.72
    00007
    -0.65
    LOG
    -0.65
    2020
    -0.64
     Tours
    -0.64
    Coun
    -0.63
    Walker
    -0.62
    KEN
    -0.62
    POSITIVE LOGITS
     prolifer
    1.16
     everywhere
    1.04
     typically
    1.04
     rarely
    1.01
     notoriously
    1.01
     plentiful
    1.00
     inherently
    0.98
     generally
    0.96
     commonplace
    0.93
     often
    0.92
    Activations Density 0.341%

    No Known Activations