© 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. 9-RES-JB
    11. 2321
    Prev
    Next
    INDEX
    Explanations

    phrases indicating uncertainty or lack of definitive information

    oai_token-act-pair · gpt-3.5-turbo

    instances of the verb "is" in various contexts

    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
    igs
    -0.70
     Locations
    -0.66
    alities
    -0.65
    yk
    -0.62
    udeau
    -0.62
    URN
    -0.61
    itus
    -0.61
    orks
    -0.61
     Blades
    -0.60
     sorts
    -0.60
    POSITIVE LOGITS
     ever
    1.43
     EVER
    1.28
     necessarily
    1.19
     anymore
    1.01
     harmed
    0.94
     remotely
    0.93
     Ever
    0.91
     imaginable
    0.89
     nor
    0.87
     spared
    0.85
    Activations Density 0.142%

    No Known Activations