Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 3613
    Prev
    Next
    INDEX
    Explanations

    references to legal, crime, and political terms

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to interrogation or questionable ethical practices

    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
    -0.59
     ):
    -0.46
    ãĥ¯ãĥ³
    -0.46
     "#
    -0.45
    é¾
    -0.45
     NFC
    -0.43
    ©¶æ¥µ
    -0.43
     "$
    -0.43
    ËĪ
    -0.42
     Riders
    -0.42
    POSITIVE LOGITS
     ..."
    1.70
    .")
    1.62
     â̦"
    1.57
    )"
    1.47
    )."
    1.46
    %"
    1.45
    ,'"
    1.42
    )",
    1.41
    ..."
    1.40
    ."[
    1.39
    Activations Density 3.139%

    No Known Activations