© 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 EvalsExportsinterp-engineNEWAPI 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. 21141
    Prev
    Next
    INDEX
    Explanations

    references to universities

    oai_token-act-pair · gpt-3.5-turbo

    mentions of universities and educational institutions

    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
    gered
    -0.58
     hydra
    -0.57
    fecture
    -0.56
     accompanied
    -0.54
     empowering
    -0.54
    nir
    -0.53
     sexually
    -0.53
     (<
    -0.53
    ienne
    -0.53
    ften
    -0.52
    POSITIVE LOGITS
     Of
    1.05
    Of
    1.01
    ModLoader
    0.89
     Manager
    0.86
     Depot
    0.86
     Square
    0.85
    Max
    0.80
     Packs
    0.77
     Wars
    0.77
    oft
    0.75
    Activations Density 0.159%

    No Known Activations