© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 22426
    Prev
    Next
    INDEX
    Explanations

    personal names, likely politicians or public figures

    oai_token-act-pair · gpt-3.5-turbo

    names or initials of individuals and specific 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
     Sounders
    -0.77
     Hydra
    -0.77
    Cub
    -0.75
    Weiss
    -0.74
     Cuban
    -0.73
     Rebels
    -0.72
     Hearts
    -0.72
     Myr
    -0.71
     Oilers
    -0.68
     Blake
    -0.68
    POSITIVE LOGITS
    umbai
    1.27
    jriwal
    1.25
    ashtra
    1.20
     Shiv
    1.18
    indu
    1.17
     Sharma
    1.14
     Bhar
    1.13
     Kumar
    1.13
    India
    1.13
     Singh
    1.12
    Activations Density 0.111%

    No Known Activations