© 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. 20948
    Prev
    Next
    INDEX
    Explanations

    words ending in "'s" indicating possession

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the letter 's' in various forms

    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
    OTAL
    -0.75
    iliate
    -0.74
    processor
    -0.66
     Pwr
    -0.66
    bp
    -0.65
    erd
    -0.64
    LIN
    -0.63
    ainers
    -0.63
    ISO
    -0.62
    rake
    -0.61
    POSITIVE LOGITS
    ullivan
    0.92
     successor
    0.87
     grandson
    0.85
     birthday
    0.80
     Revenge
    0.80
     resignation
    0.79
    kaya
    0.79
     footsteps
    0.78
     ire
    0.77
     granddaughter
    0.77
    Activations Density 0.153%

    No Known Activations