© 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. 3-RES-JB
    11. 1793
    Prev
    Next
    INDEX
    Explanations

    references to various branches and activities of military and law enforcement services

    oai_token-act-pair · gpt-3.5-turbo

    references to various military or protective forces, specifically those referred to as "Guard."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    jad
    -0.67
    piring
    -0.66
    thing
    -0.64
    dim
    -0.61
    other
    -0.60
    spread
    -0.60
    thy
    -0.60
    geon
    -0.59
    Sov
    -0.58
    ãĤ¼ãĤ¦ãĤ¹
    -0.58
    POSITIVE LOGITS
     Guard
    1.17
     Corps
    0.89
     Guards
    0.85
    andowski
    0.80
    naire
    0.75
     acad
    0.70
    aries
    0.70
    naires
    0.69
     guard
    0.69
     reserv
    0.68
    Activations Density 0.003%

    No Known Activations