© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 8-RES-JB
    6. 12424
    Prev
    Next
    INDEX
    Explanations

    text related to legal or political contexts, potentially involving controversies or investigations

    oai_token-act-pair · gpt-3.5-turbo

    references to online platforms and data privacy concerns

    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
    •Few-Token Promoting Features
    Quote Closing Feature
    •Bracket Closing Features Layer 8 GPT2 Small

    No Comments

    Negative Logits
    ãĤ´ãĥ³
    -0.65
    surprisingly
    -0.57
    xtap
    -0.52
     respectively
    -0.52
    anwhile
    -0.51
    ometimes
    -0.51
     "_
    -0.50
     "#
    -0.50
     "$
    -0.48
     <-
    -0.47
    POSITIVE LOGITS
    ,'"
    1.55
    %"
    1.51
     ..."
    1.49
    "—
    1.48
    .")
    1.46
     â̦"
    1.45
    ,"
    1.45
    )",
    1.43
    )"
    1.43
    ),"
    1.42
    Activations Density 1.952%

    No Known Activations