© 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. 3-RES-JB
    11. 545
    Prev
    Next
    INDEX
    Explanations

    keywords related to a specific technology or protocol called "Seg"

    oai_token-act-pair · gpt-3.5-turbo

    references to the Segregated Witness (SegWit) protocol in cryptocurrency discussions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Malaysian
    -0.74
     Samoa
    -0.72
     IMAGES
    -0.70
    oker
    -0.64
     haunt
    -0.64
    makers
    -0.62
    ãĤĬ
    -0.62
     Cosponsors
    -0.61
    rawdownloadcloneembedreportprint
    -0.61
     Indo
    -0.61
    POSITIVE LOGITS
    undo
    1.05
     Seg
    1.03
    lease
    0.89
    Seg
    0.85
    mentation
    0.84
    wit
    0.83
    ifts
    0.81
    regation
    0.81
    gments
    0.80
    erc
    0.79
    Activations Density 0.009%

    No Known Activations