© 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. 0-RES-JB
    11. 16628
    Prev
    Next
    INDEX
    Explanations

    words related to the name "Widener"

    oai_token-act-pair · gpt-3.5-turbo

    proper nouns, particularly names of individuals and entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    uracy
    -0.85
     hypoc
    -0.73
     ambush
    -0.72
     grate
    -0.68
    uffle
    -0.68
    erest
    -0.68
    oot
    -0.66
    arth
    -0.66
    ogue
    -0.66
     inaccur
    -0.65
    POSITIVE LOGITS
     Wid
    4.27
    wid
    1.82
     widgets
    1.27
     Tud
    1.24
     Pens
    1.06
     Boh
    1.02
     Hath
    1.02
     widget
    0.98
     Sed
    0.89
     Huss
    0.88
    Activations Density 0.044%

    No Known Activations