Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 8-RES-JB
    6. 19713
    Prev
    Next
    INDEX
    Explanations

    names of people and places, along with some related sentences

    oai_token-act-pair · gpt-3.5-turbo

    references to people and their relationships or status

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Beacon
    -0.87
     Monroe
    -0.87
     Wilmington
    -0.81
     Becky
    -0.79
     Tacoma
    -0.78
     Myr
    -0.77
     Spokane
    -0.76
     Abby
    -0.76
     Hydra
    -0.76
     Syracuse
    -0.75
    POSITIVE LOGITS
     Singh
    1.49
     Sharma
    1.44
     Kumar
    1.42
     Pradesh
    1.38
    jriwal
    1.35
     Gujarat
    1.32
     Punjab
    1.32
    umbai
    1.31
     Maharashtra
    1.31
     Bhar
    1.28
    Activations Density 1.769%

    No Known Activations