© 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
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 11-RES-JB
    11. 20784
    Prev
    Next
    INDEX
    Explanations

    names of prominent individuals or celebrities

    oai_token-act-pair · gpt-3.5-turbo

    proper names, particularly surnames or significant individuals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Newark
    -0.86
     Liberty
    -0.73
     Burlington
    -0.71
     sail
    -0.69
     Tripoli
    -0.68
     capacitor
    -0.68
     Essex
    -0.68
     hemp
    -0.66
     maritime
    -0.66
     FreeBSD
    -0.66
    POSITIVE LOGITS
    âĢ
    2.02
     âĢ
    1.48
    âĢł
    1.05
    âģ
    0.97
    áµ
    0.94
    à¼
    0.93
    ãĢ
    0.93
    âķIJ
    0.92
    âĸ
    0.91
    enegger
    0.90
    Activations Density 0.369%

    No Known Activations