© 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. 23721
    Prev
    Next
    INDEX
    Explanations

    people, things, or events introduced with the word "meanwhile."

    oai_token-act-pair · gpt-3.5-turbo

    the word "meanwhile" and its 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
    enders
    -0.80
    ized
    -0.73
    ends
    -0.73
    omical
    -0.72
    amed
    -0.71
    kind
    -0.71
    oric
    -0.70
    ending
    -0.70
    ender
    -0.69
    uto
    -0.68
    POSITIVE LOGITS
    æ©Ł
    0.82
    é¾įåĸļ士
    0.79
    ãĤ´ãĥ³
    0.77
    ðĿ
    0.76
    wcs
    0.76
    ãĥķãĤ©
    0.73
     exha
    0.72
     langu
    0.70
    EStream
    0.69
    åĤ
    0.66
    Activations Density 0.006%

    No Known Activations