© 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. 1-RES-JB
    11. 3613
    Prev
    Next
    INDEX
    Explanations

    proper nouns, specifically the name "Knight" with variations in numerical values

    oai_token-act-pair · gpt-3.5-turbo

    references to a character named Knight

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    obos
    -0.73
    pty
    -0.72
    ential
    -0.71
    andem
    -0.71
    posium
    -0.71
    istors
    -0.70
    ional
    -0.70
    eph
    -0.67
    imester
    -0.67
    istor
    -0.66
    POSITIVE LOGITS
     Knight
    1.23
     Templar
    1.20
    mare
    1.13
    mares
    1.04
    holder
    1.01
     Knights
    0.88
     Templ
    0.88
     knight
    0.86
     Rider
    0.85
    Knight
    0.85
    Activations Density 0.009%

    No Known Activations