© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 4-RES-JB
    6. 11353
    Prev
    Next
    INDEX
    Explanations

    the word "Knight" in varying contexts

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the name "Knight."

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

    No Comments

    Negative Logits
    ional
    -0.82
    mble
    -0.78
    ascus
    -0.76
    orship
    -0.71
    ience
    -0.70
    ources
    -0.67
    istor
    -0.67
    acity
    -0.67
    ITIES
    -0.67
    ophob
    -0.67
    POSITIVE LOGITS
    mare
    1.31
     Templar
    1.28
    mares
    1.18
     Knight
    1.03
    fish
    1.02
    holder
    0.97
    doms
    0.92
     Templ
    0.92
    fighter
    0.87
     knight
    0.87
    Activations Density 0.014%

    No Known Activations