© 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. 1-RES-JB
    6. 5345
    Prev
    Next
    INDEX
    Explanations

    mentions of the position "deputy"

    oai_token-act-pair · gpt-3.5-turbo

    references to the term "deputy" in various contexts

    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
     Gutenberg
    -0.78
    etts
    -0.78
    uph
    -0.77
    ebook
    -0.77
    stakes
    -0.76
    orem
    -0.76
    yrs
    -0.75
    eka
    -0.74
    76561
    -0.74
    oven
    -0.74
    POSITIVE LOGITS
     deputy
    1.22
    uty
    1.12
     assistant
    0.98
     Deputy
    0.92
     clerks
    0.86
     glim
    0.83
     lieutenant
    0.83
     chief
    0.81
     deputies
    0.80
     Assistant
    0.79
    Activations Density 0.010%

    No Known Activations