© 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. 1335
    Prev
    Next
    INDEX
    Explanations

    words related to tasks or actions requiring effort or coordination

    oai_token-act-pair · gpt-3.5-turbo

    concepts related to planning, organization, and classification

    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
     Worldwide
    -0.64
    enegger
    -0.61
     Zimbabwe
    -0.57
     Qiao
    -0.57
     Hots
    -0.56
     Uganda
    -0.55
     Zam
    -0.54
     Haram
    -0.54
     Composite
    -0.53
     Newsp
    -0.53
    POSITIVE LOGITS
    coin
    0.83
    hack
    0.71
    card
    0.65
    hole
    0.64
    coins
    0.64
    marks
    0.63
    bike
    0.63
    pack
    0.63
    league
    0.62
    plot
    0.61
    Activations Density 0.768%

    No Known Activations