© 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. 11-RES-JB
    11. 21685
    Prev
    Next
    INDEX
    Explanations

    phrases describing anticipation or waiting for something

    oai_token-act-pair · gpt-3.5-turbo

    the presence of contractions indicating speech or thought processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     mixed
    -0.63
     revolutionaries
    -0.61
     Revolution
    -0.60
     GC
    -0.60
     prior
    -0.59
     radicals
    -0.59
     division
    -0.59
     favors
    -0.58
     partners
    -0.58
     multiplying
    -0.58
    POSITIVE LOGITS
    itely
    1.03
    t
    1.02
    idate
    1.02
    tal
    0.93
    ationally
    0.91
    Ķ
    0.90
    tain
    0.89
    ulty
    0.87
    ibly
    0.86
    ency
    0.85
    Activations Density 0.103%

    No Known Activations