© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 6928
    Prev
    Next
    INDEX
    Explanations

    the word "whim" or variants of it

    oai_token-act-pair · gpt-3.5-turbo

    references to unpredictability or capricious behavior

    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
     seq
    -0.74
    ainers
    -0.70
     Sacrament
    -0.69
     Journals
    -0.69
     Pict
    -0.68
     Substance
    -0.66
     Protestants
    -0.66
     Kear
    -0.66
     Dakota
    -0.65
    atchewan
    -0.63
    POSITIVE LOGITS
     whim
    1.40
     whims
    1.27
    pering
    1.07
    sy
    1.01
    istically
    0.97
    fy
    0.94
    itory
    0.86
    ulously
    0.81
    bley
    0.80
     flick
    0.80
    Activations Density 0.009%

    No Known Activations