© 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. 10-RES-JB
    11. 18819
    Prev
    Next
    INDEX
    Explanations

    mentions of quantities and specific entities like money, animals, or items being given or received

    oai_token-act-pair · gpt-3.5-turbo

    monetary values and significant quantities

    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
     DOE
    -1.00
     Autism
    -0.89
     GMOs
    -0.82
     VIDEO
    -0.81
     meltdown
    -0.81
     Millennials
    -0.81
    ETA
    -0.81
     Pixar
    -0.81
     morphed
    -0.80
     VIDEOS
    -0.80
    POSITIVE LOGITS
     nobles
    1.44
     lords
    1.30
     knights
    1.30
     nobility
    1.28
     royal
    1.23
     cavalry
    1.21
     garrison
    1.20
     princes
    1.20
     palace
    1.19
     consec
    1.18
    Activations Density 0.807%

    No Known Activations