© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 1-RES-JB
    6. 12974
    Prev
    Next
    INDEX
    Explanations

    the word "whim."

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "whim" and related variations expressing spontaneity or capriciousness

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Pict
    -0.76
     Rhod
    -0.74
     Cheong
    -0.70
     Journals
    -0.68
     Sachs
    -0.68
     Prescott
    -0.66
     Alt
    -0.66
     Pacers
    -0.65
    ______
    -0.65
    ranked
    -0.64
    POSITIVE LOGITS
     whim
    1.62
     whims
    1.16
    pering
    1.16
    fy
    1.01
    istically
    0.96
    pered
    0.91
    bley
    0.88
    bly
    0.88
    itory
    0.87
    sy
    0.86
    Activations Density 0.011%

    No Known Activations