© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 6978
    Prev
    Next
    INDEX
    Explanations

    the word "And" at the start of a sentence

    oai_token-act-pair · gpt-3.5-turbo

    repeated conjunctions, particularly the word "And."

    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
    ãģĨ
    -0.61
    /"
    -0.52
     Retrieved
    -0.51
     (âĪĴ
    -0.51
    Contents
    -0.51
    BuyableInstoreAndOnline
    -0.51
     Unloaded
    -0.50
     anten
    -0.49
    Thumbnail
    -0.49
    pmwiki
    -0.48
    POSITIVE LOGITS
    romeda
    1.70
    rea
    1.55
    ersen
    1.37
    hra
    1.30
    ré
    1.29
    alus
    1.18
     secondly
    1.09
    rey
    1.08
    rogens
    1.03
     therein
    1.02
    Activations Density 0.097%

    No Known Activations