© 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
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 4-RES-JB
    11. 7567
    Prev
    Next
    INDEX
    Explanations

    proper nouns, specifically focusing on names like "Ginsburg" and "Marilyn."

    oai_token-act-pair · gpt-3.5-turbo

    mentions of specific individuals and their associated sentiments

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

    No Comments

    Negative Logits
    quickShipAvailable
    -0.68
    TPPStreamerBot
    -0.67
    ague
    -0.62
    llah
    -0.61
    channelAvailability
    -0.61
    ansas
    -0.60
    eting
    -0.58
    Laun
    -0.58
     Mehran
    -0.58
    riage
    -0.57
    POSITIVE LOGITS
    uria
    0.91
    ergic
    0.86
    ationally
    0.85
    ured
    0.83
    selage
    0.83
    itial
    0.82
    orial
    0.82
    urally
    0.79
    vir
    0.73
    atur
    0.72
    Activations Density 0.019%

    No Known Activations