© 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. 19029
    Prev
    Next
    INDEX
    Explanations

    capitalized words related to authority or official titles

    oai_token-act-pair · gpt-3.5-turbo

    key concepts related to governance, societal structures, and information

    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
     vain
    -0.72
     straw
    -0.70
    terday
    -0.67
     republican
    -0.63
    anwhile
    -0.63
     trail
    -0.62
     forestry
    -0.61
     nipple
    -0.61
     nursing
    -0.61
     studios
    -0.61
    POSITIVE LOGITS
     Month
    0.96
     Characters
    0.95
     Period
    0.94
     Day
    0.93
     Points
    0.92
     Era
    0.92
     Ones
    0.92
     Order
    0.90
     Position
    0.90
    Ship
    0.89
    Activations Density 0.506%

    No Known Activations