© 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. 13819
    Prev
    Next
    INDEX
    Explanations

    mentions of a specific name "Thayer"

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the term "ayer," which seems to relate to a specific individual or topic within the context

    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
     Sop
    -0.68
    encers
    -0.67
     swollen
    -0.66
    è¯
    -0.64
     neigh
    -0.62
    İĭ
    -0.61
     quaint
    -0.61
    orate
    -0.59
    inished
    -0.59
    encing
    -0.57
    POSITIVE LOGITS
    ayer
    1.38
    ayers
    1.02
    mare
    0.89
    pillar
    0.82
    rower
    0.78
    ware
    0.76
    getic
    0.75
    aid
    0.73
    deen
    0.71
    tenance
    0.71
    Activations Density 0.014%

    No Known Activations