© 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. 10-RES-JB
    11. 11469
    Prev
    Next
    INDEX
    Explanations

    exceptions or contrasts in a context

    oai_token-act-pair · gpt-3.5-turbo

    the word "except" and its variations, highlighting exceptions or contrasts in statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    pires
    -0.66
     Flavoring
    -0.64
    natureconservancy
    -0.62
    intel
    -0.56
    llah
    -0.56
    utra
    -0.54
    ked
    -0.54
     parsed
    -0.54
    ULT
    -0.54
    urity
    -0.53
    POSITIVE LOGITS
    ional
    1.48
     insofar
    1.06
    ing
    1.06
     maybe
    0.90
     perhaps
    0.86
     for
    0.81
     possibly
    0.74
    arus
    0.71
    ably
    0.71
    ed
    0.70
    Activations Density 0.031%

    No Known Activations