© 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
    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. 20995
    Prev
    Next
    INDEX
    Explanations

    sentences that express uncertainty or doubt

    oai_token-act-pair · gpt-3.5-turbo

    the word "Perhaps" which indicates uncertainty or speculation

    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
     blender
    -0.69
    natureconservancy
    -0.68
    plings
    -0.67
    opal
    -0.67
    lisher
    -0.67
    itiz
    -0.66
    irements
    -0.66
    perature
    -0.65
    ARS
    -0.64
    ancial
    -0.63
    POSITIVE LOGITS
    ²¾
    0.72
     Perhaps
    0.70
     Maybe
    0.69
    Perhaps
    0.65
     unsurprisingly
    0.65
     Worlds
    0.65
    Interested
    0.64
    soever
    0.64
     Interest
    0.64
     Tomorrow
    0.63
    Activations Density 0.017%

    No Known Activations