© 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. 23128
    Prev
    Next
    INDEX
    Explanations

    adverbs

    oai_token-act-pair · gpt-3.5-turbo

    adverbs indicating frequency or manner

    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
     Central
    -0.51
     Cohen
    -0.51
     Vernon
    -0.49
     Organization
    -0.48
     Thornton
    -0.47
     Lon
    -0.47
     ÂŃ
    -0.46
     Organisation
    -0.46
     Jur
    -0.45
    Cour
    -0.45
    POSITIVE LOGITS
     recommends
    0.93
     qualifies
    0.92
     detects
    0.92
     destroys
    0.91
     solves
    0.90
     sells
    0.89
     refers
    0.89
     sucks
    0.89
     removes
    0.89
     enhances
    0.88
    Activations Density 0.173%

    No Known Activations