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. 10-RES-JB
    6. 22567
    Prev
    Next
    INDEX
    Explanations

    names of people and places mentioned in news articles

    oai_token-act-pair · gpt-3.5-turbo

    mentions of individuals, particularly prominent figures or public officials

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Egypt
    -1.17
    NBA
    -1.09
     Memphis
    -1.06
     Tacoma
    -1.02
     Grizzlies
    -1.00
     Mubarak
    -0.99
     Bezos
    -0.97
     Wichita
    -0.95
     Egyptians
    -0.95
     Egyptian
    -0.94
    POSITIVE LOGITS
    Ireland
    1.97
     Dublin
    1.93
    Irish
    1.92
     Irish
    1.92
     Ireland
    1.87
     Cork
    1.75
     Ulster
    1.74
     Gael
    1.64
     Sinn
    1.63
     TDs
    1.52
    Activations Density 0.355%

    No Known Activations