© 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. 3-RES-JB
    11. 15798
    Prev
    Next
    INDEX
    Explanations

    names of characters and locations from a fantasy world

    oai_token-act-pair · gpt-3.5-turbo

    prominently mentioned names and significant characters in a narrative context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     MX
    -0.87
    trak
    -0.85
    ï¸ı
    -0.79
    ronics
    -0.78
    -+-+
    -0.78
    Report
    -0.70
    eering
    -0.69
    Īè
    -0.68
     Zucker
    -0.68
    Bernie
    -0.68
    POSITIVE LOGITS
     Tolkien
    0.97
     elves
    0.94
    Spoiler
    0.88
     Lann
    0.88
     Elves
    0.85
     robes
    0.82
    olkien
    0.82
     Elven
    0.82
    ampire
    0.79
     reborn
    0.79
    Activations Density 0.257%

    No Known Activations