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. 13129
    Prev
    Next
    INDEX
    Explanations

    proper nouns related to political figures and events

    oai_token-act-pair · gpt-3.5-turbo

    instances of speeches made by prominent figures

    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
    EStreamFrame
    -0.76
    mol
    -0.76
     fingert
    -0.72
    aea
    -0.70
    sci
    -0.70
    stice
    -0.66
     eyeb
    -0.66
    pection
    -0.65
     reuse
    -0.65
    pha
    -0.65
    POSITIVE LOGITS
     President
    1.89
     Barack
    1.77
     Hillary
    1.57
     Obama
    1.57
     Donald
    1.55
    President
    1.54
     Trump
    1.53
     Senator
    1.50
     Secretary
    1.47
     president
    1.42
    Activations Density 0.487%

    No Known Activations