© 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. 1-RES-JB
    11. 3486
    Prev
    Next
    INDEX
    Explanations

    the word "opt" or variations of it

    oai_token-act-pair · gpt-3.5-turbo

    variations of the word "opt" and related concepts

    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
     Kah
    -0.70
     Laur
    -0.64
     Cros
    -0.64
    ̶
    -0.63
    gb
    -0.61
    Series
    -0.59
     Monte
    -0.59
    ioxide
    -0.59
     Kag
    -0.57
     Trib
    -0.57
    POSITIVE LOGITS
    opt
    1.35
    imum
    1.09
     opt
    0.95
    imal
    0.88
    isphere
    0.85
    anical
    0.83
    imus
    0.81
    ICAL
    0.81
    ypes
    0.81
    asus
    0.80
    Activations Density 0.003%

    No Known Activations