© 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. 6-RES-JB
    11. 17383
    Prev
    Next
    INDEX
    Explanations

    acronyms or abbreviations with the letters 'ym' in them

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the string "ym."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Aires
    -0.76
     Rica
    -0.68
    Benz
    -0.66
    DERR
    -0.65
     Paragu
    -0.63
    Ùĩ
    -0.62
    IVES
    -0.62
    hold
    -0.62
    OPLE
    -0.61
    enhagen
    -0.61
    POSITIVE LOGITS
    ptoms
    1.26
    otor
    1.09
    posium
    1.06
    pson
    1.03
    aceutical
    1.01
    otive
    0.87
    otion
    0.87
    oly
    0.87
    oti
    0.86
    ohyd
    0.86
    Activations Density 0.016%

    No Known Activations