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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 8-RES-JB
    11. 6249
    Prev
    Next
    INDEX
    Explanations

    the word "que"

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "que" indicating questioning or inquiries

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ronics
    -0.69
    opathy
    -0.65
     ICC
    -0.64
     FANT
    -0.64
     bats
    -0.63
     OD
    -0.63
     Realms
    -0.63
     endanger
    -0.63
    ARC
    -0.62
    ãĤ¼ãĤ¦ãĤ¹
    -0.60
    POSITIVE LOGITS
    uing
    1.17
    ued
    1.14
    erness
    1.14
    ues
    1.04
    zon
    1.00
    uers
    0.96
    zar
    0.94
    ue
    0.88
    lez
    0.86
    ero
    0.86
    Activations Density 0.016%

    No Known Activations