© 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. 0-RES-JB
    6. 14720
    Prev
    Next
    INDEX
    Explanations

    phrases beginning with "And"

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "And"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     due
    -0.75
     preferred
    -0.66
     classified
    -0.66
     planned
    -0.64
     carriage
    -0.63
     favorable
    -0.63
     considered
    -0.62
     intended
    -0.61
     comm
    -0.61
     cens
    -0.60
    POSITIVE LOGITS
    And
    2.99
     And
    1.85
    Then
    1.85
    But
    1.80
    Which
    1.73
    So
    1.67
    That
    1.64
    Indeed
    1.57
    Again
    1.56
    Or
    1.54
    Activations Density 0.026%

    No Known Activations