© 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. 2-RES-JB
    11. 23689
    Prev
    Next
    INDEX
    Explanations

    exact adverbs or adjectives that enhance the precision or accuracy of an action or situation

    oai_token-act-pair · gpt-3.5-turbo

    the term "precisely" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Mushroom
    -0.70
    abies
    -0.67
     BYU
    -0.67
     Rudd
    -0.66
    TRY
    -0.65
    ocene
    -0.64
    ker
    -0.64
    asta
    -0.64
    oki
    -0.63
     Staples
    -0.62
    POSITIVE LOGITS
    uracy
    0.75
     calibrated
    0.71
     deline
    0.68
    ettings
    0.68
    yrinth
    0.67
     tailored
    0.67
     precisely
    0.66
    arist
    0.66
    uner
    0.66
    initions
    0.66
    Activations Density 0.003%

    No Known Activations