© 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. 10426
    Prev
    Next
    INDEX
    Explanations

    phrases involving the word "wide" as an adjective

    oai_token-act-pair · gpt-3.5-turbo

    the term "wide" in 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
    ilater
    -0.76
     Tribe
    -0.69
     Epstein
    -0.68
     Aliens
    -0.65
    ourke
    -0.65
     FANT
    -0.63
     Tempest
    -0.62
     Peb
    -0.61
     Templ
    -0.60
     Beasts
    -0.59
    POSITIVE LOGITS
    wide
    1.15
    sheet
    0.95
    sheets
    0.93
    keye
    0.88
    creen
    0.87
    leaf
    0.84
    entimes
    0.82
    vine
    0.77
    foundland
    0.76
    etheless
    0.75
    Activations Density 0.008%

    No Known Activations