© 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. 2763
    Prev
    Next
    INDEX
    Explanations

    names of political figures and medical terms

    oai_token-act-pair · gpt-3.5-turbo

    specific numerical data and statistics in the text

    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
    âĢ
    -0.63
    ÂŃ
    -0.55
     âĢ
    -0.54
    âĻ¦
    -0.53
    ¶
    -0.50
    —
    -0.50
    âĻ
    -0.48
    â
    -0.48
    ––
    -0.48
    âĢł
    -0.47
    POSITIVE LOGITS
     entit
    0.32
     english
    0.31
     apartheid
    0.30
     mentioning
    0.29
     neighbouring
    0.27
     Urug
    0.27
     natives
    0.27
     thereto
    0.27
     Sharia
    0.26
     extinct
    0.26
    Activations Density 2.660%

    No Known Activations