© 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. 10259
    Prev
    Next
    INDEX
    Explanations

    proper nouns (names) ending in 'marsh'

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the name "Marsh" or similar high-frequency terms

    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
     trickle
    -0.72
     duct
    -0.64
     boil
    -0.63
     developing
    -0.62
     crawl
    -0.62
     transitional
    -0.61
     tense
    -0.61
    existent
    -0.59
     commercially
    -0.58
     eBay
    -0.57
    POSITIVE LOGITS
    arsh
    1.37
    mallow
    1.26
    adow
    1.02
    rawdownloadcloneembedreportprint
    0.93
    ãĥ¥
    0.91
     ILCS
    0.89
    abulary
    0.85
    ield
    0.83
    ãĤ¦ãĤ¹
    0.77
    Ó
    0.76
    Activations Density 0.004%

    No Known Activations