© 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. 11-RES-JB
    11. 7638
    Prev
    Next
    INDEX
    Explanations

    proper nouns or titles within the text, particularly related to entertainment or technology

    oai_token-act-pair · gpt-3.5-turbo

    titles and terms related to video games, specifically those associated with the "Final Fantasy" series and other gaming franchises

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     trough
    -0.78
     administr
    -0.78
    lessly
    -0.78
    igning
    -0.77
    lets
    -0.75
     depend
    -0.74
     dens
    -0.72
    let
    -0.71
     formal
    -0.71
     relative
    -0.71
    POSITIVE LOGITS
     Warfare
    1.40
     Carnage
    1.23
     Mayhem
    1.16
     Warrior
    1.16
     Struggle
    1.15
     Machines
    1.11
     Limits
    1.10
     Concepts
    1.09
     Grounds
    1.08
     Shooter
    1.08
    Activations Density 0.217%

    No Known Activations