© 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. 10-RES-JB
    11. 11577
    Prev
    Next
    INDEX
    Explanations

    commands or instructions written in a specific format

    oai_token-act-pair · gpt-3.5-turbo

    currency symbols and monetary values

    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
     Moody
    -0.71
     produ
    -0.67
     Goldstein
    -0.66
     Dunk
    -0.65
     Sed
    -0.65
     Gors
    -0.65
     Amber
    -0.64
     assum
    -0.64
     Wolfe
    -0.63
     Bri
    -0.63
    POSITIVE LOGITS
    HOME
    1.14
    GOP
    1.07
    true
    1.06
    false
    1.04
    this
    0.99
    _.
    0.98
    True
    0.97
    EDIT
    0.91
    tw
    0.90
    tm
    0.89
    Activations Density 0.019%

    No Known Activations