© 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 EvalsExportsinterp-engineNEWAPI 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. 9-RES-JB
    11. 11721
    Prev
    Next
    INDEX
    Explanations

    phrases containing the word "what"

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "what" and related phrases indicating uncertainty or inquiry

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    erate
    -0.73
    odge
    -0.70
    geoning
    -0.65
    Ĥİ
    -0.65
    eln
    -0.65
    ulkan
    -0.63
    luster
    -0.62
    inence
    -0.62
    owsky
    -0.62
    eri
    -0.61
    POSITIVE LOGITS
     happened
    1.11
     happens
    1.07
     transpired
    0.99
     happ
    0.98
     constitutes
    0.94
     kinds
    0.93
     kind
    0.90
    soever
    0.79
     exactly
    0.79
     else
    0.77
    Activations Density 0.066%

    No Known Activations