© 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. 8-RES-JB
    11. 8217
    Prev
    Next
    INDEX
    Explanations

    keywords related to the video game "Skyrim" and the gaming company "Bethesda."

    oai_token-act-pair · gpt-3.5-turbo

    references to the video games "Skyrim" and "Fallout."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    •single token firings
    Individually fires on " Skyrim", " Morrow", " Oblivion", "yrim", " Bethesda", ... " Fallout", ...

    No Comments

    Negative Logits
    arnaev
    -1.01
    ailand
    -0.81
    arding
    -0.80
    dinand
    -0.80
    ablishment
    -0.76
    aucus
    -0.74
    atta
    -0.73
    rikes
    -0.73
    zac
    -0.73
    aminer
    -0.73
    POSITIVE LOGITS
     Skyrim
    0.82
     Scrolls
    0.77
    Leaks
    0.75
     Oblivion
    0.73
     Fallout
    0.70
    nexus
    0.68
    âĶĢ
    0.67
    Reloaded
    0.67
     Frey
    0.65
    Detailed
    0.64
    Activations Density 0.087%

    No Known Activations