© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 11-RES-JB
    6. 6750
    Prev
    Next
    INDEX
    Explanations

    proper names or specific terms related to individuals or entities

    oai_token-act-pair · gpt-3.5-turbo

    names of individuals, particularly public figures or notable personalities

    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
     Hurricanes
    -0.77
     Newfoundland
    -0.66
     Dhabi
    -0.64
     Por
    -0.61
     Laos
    -0.59
     Pixie
    -0.59
    sburgh
    -0.59
     Mae
    -0.59
     Crimean
    -0.59
     Crom
    -0.58
    POSITIVE LOGITS
    etz
    0.70
    zinski
    0.68
    oyer
    0.65
    eman
    0.65
    bart
    0.65
    dry
    0.64
    insky
    0.64
    mann
    0.63
    zynski
    0.63
     answ
    0.63
    Activations Density 0.172%

    No Known Activations