© 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. 8-RES-JB
    11. 12255
    Prev
    Next
    INDEX
    Explanations

    phrases indicating uncertainty or lack of definitive information

    oai_token-act-pair · gpt-3.5-turbo

    phrases expressing uncertainty or the lack of definitive knowledge

    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
    ngth
    -0.64
    ipel
    -0.63
     Resist
    -0.63
     Converted
    -0.63
    cit
    -0.60
    jet
    -0.60
    itton
    -0.59
     Dil
    -0.58
    igi
    -0.57
    ortment
    -0.56
    POSITIVE LOGITS
     nor
    1.14
     anymore
    1.10
     definitively
    0.99
     specifics
    0.99
     definitive
    0.90
     exact
    0.88
     yet
    0.85
     conclusive
    0.84
     anything
    0.80
     decipher
    0.78
    Activations Density 0.344%

    No Known Activations