© 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. 10-RES-JB
    11. 16562
    Prev
    Next
    INDEX
    Explanations

    phrases indicating curiosity or doubt

    oai_token-act-pair · gpt-3.5-turbo

    expressions of curiosity or contemplation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    onica
    -0.56
    rites
    -0.55
    ONG
    -0.55
    itual
    -0.55
    oided
    -0.54
    ortunately
    -0.54
    orest
    -0.53
    legates
    -0.51
    uctions
    -0.51
    absor
    -0.50
    POSITIVE LOGITS
     aloud
    1.42
     why
    1.41
     whether
    1.31
    why
    1.29
     WHY
    1.29
     how
    1.25
     if
    1.12
    whether
    1.09
     HOW
    1.06
    how
    1.02
    Activations Density 0.043%

    No Known Activations