© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 10-RES-JB
    11. 21919
    Prev
    Next
    INDEX
    Explanations

    news-related keywords or entities

    oai_token-act-pair · gpt-3.5-turbo

    references to news media outlets

    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
    ught
    -0.70
    Äĩ
    -0.65
    vernment
    -0.65
     jerk
    -0.64
    uations
    -0.62
    uras
    -0.62
    vasive
    -0.61
    hetti
    -0.59
     territorial
    -0.59
    versions
    -0.59
    POSITIVE LOGITS
    letters
    1.16
    flash
    1.10
    groups
    0.99
    room
    0.98
    letter
    0.98
    BTC
    0.95
    busters
    0.92
    peak
    0.91
    Center
    0.88
    week
    0.85
    Activations Density 0.027%

    No Known Activations