© 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. 3407
    Prev
    Next
    INDEX
    Explanations

    words related to a specific region or entity called "Skidmore."

    oai_token-act-pair · gpt-3.5-turbo

    specific names or references to buildings, institutions, or locations

    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
    uez
    -0.69
    CLOSE
    -0.59
    -+-+
    -0.56
     cornerstone
    -0.55
     @@
    -0.55
    Wan
    -0.55
    \\\\\\\\
    -0.55
    INO
    -0.55
    ACTED
    -0.54
    OUP
    -0.54
    POSITIVE LOGITS
    bucks
    0.94
    buck
    0.94
    ibaba
    0.92
    lde
    0.86
    iland
    0.86
    addle
    0.80
    inav
    0.78
    ulkan
    0.74
    halla
    0.73
    odan
    0.73
    Activations Density 0.074%

    No Known Activations