© 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. 23238
    Prev
    Next
    INDEX
    Explanations

    phrases indicating uncertainty or a choice between options

    oai_token-act-pair · gpt-3.5-turbo

    alternative options or hypotheses in a question format

    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
    then
    -0.65
    vertising
    -0.65
    URA
    -0.64
    onde
    -0.63
    ãĤ´
    -0.61
    Ãį
    -0.60
    thank
    -0.59
    sted
    -0.58
    URRENT
    -0.57
    sound
    -0.56
    POSITIVE LOGITS
     whether
    1.17
    acular
    1.03
    nam
    1.00
    acle
    0.98
    acles
    0.96
     merely
    0.94
    chard
    0.91
    ifice
    0.89
     else
    0.87
     alternatively
    0.87
    Activations Density 0.098%

    No Known Activations