© 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. 20938
    Prev
    Next
    INDEX
    Explanations

    names related to people and places

    oai_token-act-pair · gpt-3.5-turbo

    specific names and terms related to individuals or entities

    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
     Eck
    -0.62
     cod
    -0.59
     Ness
    -0.58
    Wolf
    -0.56
    Cath
    -0.56
     Comet
    -0.56
     Eleanor
    -0.55
    Beck
    -0.55
     WW
    -0.54
     homophobic
    -0.54
    POSITIVE LOGITS
    obin
    0.95
    nir
    0.92
    enei
    0.91
    chev
    0.90
    ogg
    0.87
    arij
    0.85
    arov
    0.80
    endar
    0.80
    afi
    0.79
    src
    0.76
    Activations Density 0.066%

    No Known Activations