© 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. 11-RES-JB
    11. 21133
    Prev
    Next
    INDEX
    Explanations

    phrases related to expressing doubt or opposition

    oai_token-act-pair · gpt-3.5-turbo

    expressions of uncertainty or skepticism

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    dayName
    -0.96
    isode
    -0.75
    ĸļ
    -0.75
    cffff
    -0.74
     Dragonbound
    -0.74
    ESE
    -0.74
    Located
    -0.74
    ]).
    -0.73
    reated
    -0.72
    ļéĨĴ
    -0.72
    POSITIVE LOGITS
     occasional
    1.31
     some
    1.15
     occasionally
    1.04
     sometimes
    1.01
     exceptions
    0.91
     faults
    0.90
     SOME
    0.90
     detractors
    0.89
    some
    0.88
     inconven
    0.85
    Activations Density 0.423%

    No Known Activations