© 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. 7-RES-JB
    6. 23701
    Prev
    Next
    INDEX
    Explanations

    geographical locations such as cities and countries

    oai_token-act-pair · gpt-3.5-turbo

    references to locations or geographic areas

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    DragonMagazine
    -0.83
     voices
    -0.74
    0000000000000000
    -0.69
    avier
    -0.67
    potion
    -0.67
    poons
    -0.66
    xon
    -0.65
    GAN
    -0.65
    mails
    -0.64
    bol
    -0.64
    POSITIVE LOGITS
     southern
    0.95
     southwestern
    0.95
     northeastern
    0.94
     eastern
    0.94
     Southeast
    0.90
     northern
    0.90
     Eastern
    0.87
     Mississ
    0.87
     southeastern
    0.86
     populous
    0.85
    Activations Density 0.263%

    No Known Activations