© 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. 11-RES-JB
    11. 172
    Prev
    Next
    INDEX
    Explanations

    words or phrases that start with "Wh" followed by a high activation word or phrase

    oai_token-act-pair · gpt-3.5-turbo

    repeated uses of the word "wh" in various forms, indicating a focus on questioning or inquiry concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     reasoned
    -0.66
     incub
    -0.66
     anyway
    -0.64
     theirs
    -0.64
     revolving
    -0.62
     Grande
    -0.62
     flares
    -0.61
     Duo
    -0.61
     styled
    -0.61
     Feder
    -0.60
    POSITIVE LOGITS
    ichever
    1.59
    istle
    1.59
    ilst
    1.58
    oles
    1.44
    ispers
    1.42
    ole
    1.42
    ats
    1.35
    omever
    1.35
    olly
    1.34
    irlwind
    1.33
    Activations Density 0.012%

    No Known Activations