© 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. 9-RES-JB
    11. 17073
    Prev
    Next
    INDEX
    Explanations

    quotations, especially ones related to commands or instructions

    oai_token-act-pair · gpt-3.5-turbo

    instances of quotation marks surrounding various phrases or statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Archdemon
    -0.80
     chair
    -0.74
     Klu
    -0.71
     outfielder
    -0.71
     Vog
    -0.70
     Concord
    -0.70
     division
    -0.70
     candles
    -0.69
     Chair
    -0.68
     foreseeable
    -0.68
    POSITIVE LOGITS
    normal
    1.55
    cheat
    1.49
    official
    1.48
    natural
    1.40
    traditional
    1.36
    pure
    1.36
    safe
    1.36
    clean
    1.35
    classic
    1.34
    soft
    1.34
    Activations Density 0.129%

    No Known Activations