© 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. 0-RES-JB
    11. 15546
    Prev
    Next
    INDEX
    Explanations

    a common text separator "As" at the beginning of sentences

    oai_token-act-pair · gpt-3.5-turbo

    instances of the phrase "As [value]" indicating transition or emphasis

    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
    kered
    -0.72
    vable
    -0.70
    itely
    -0.65
    mable
    -0.63
    yers
    -0.63
    imes
    -0.63
    quart
    -0.60
    itton
    -0.58
    icz
    -0.58
    icle
    -0.57
    POSITIVE LOGITS
     As
    2.70
    As
    1.78
     At
    1.69
     In
    1.40
     To
    1.40
     By
    1.38
     While
    1.37
     An
    1.34
     On
    1.33
     For
    1.32
    Activations Density 0.026%

    No Known Activations