© 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. 10-RES-JB
    11. 11636
    Prev
    Next
    INDEX
    Explanations

    words related to storytelling or events

    oai_token-act-pair · gpt-3.5-turbo

    keywords related to narratives and legal or procedural contexts

    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
    tics
    -0.89
    ernels
    -0.86
     VIDEOS
    -0.72
    sites
    -0.66
    drops
    -0.66
     Dragonbound
    -0.66
    itudes
    -0.65
     Empires
    -0.64
    ampires
    -0.64
    aughs
    -0.62
    POSITIVE LOGITS
     called
    0.89
     titled
    0.88
     Called
    0.86
     resembling
    0.85
    itled
    0.82
     dubbed
    0.82
     named
    0.81
    numbered
    0.78
    called
    0.74
     originally
    0.72
    Activations Density 0.397%

    No Known Activations