© 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. 21089
    Prev
    Next
    INDEX
    Explanations

    phrases that include the word "said"

    oai_token-act-pair · gpt-3.5-turbo

    instances of attribution or quotations in speech

    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
    ãĥİ
    -0.65
    OIL
    -0.64
    ãĥĥãĥī
    -0.63
    pend
    -0.61
    found
    -0.57
    ãĥĥãĥĪ
    -0.56
    ãĥł
    -0.56
    ãĥij
    -0.53
    Operation
    -0.53
    ãĥª
    -0.52
    POSITIVE LOGITS
     afterward
    0.86
     bluntly
    0.85
     sarcast
    0.85
    .
    0.83
     rhet
    0.82
     emphatically
    0.76
     softly
    0.76
     incred
    0.75
     of
    0.75
     laughing
    0.72
    Activations Density 0.112%

    No Known Activations