© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 10258
    Prev
    Next
    INDEX
    Explanations

    instances where the word "say" is used in various contexts or expressions

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "say" and its variations

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Negative Logits
    xtap
    -0.78
    ockets
    -0.76
    mania
    -0.70
    pleting
    -0.65
    gotten
    -0.64
    olars
    -0.62
     Firearms
    -0.61
    ritional
    -0.61
     largeDownload
    -0.60
    mental
    -0.59
    POSITIVE LOGITS
     goodbye
    1.70
     hello
    1.33
     aloud
    1.21
     farewell
    1.14
     Goodbye
    1.07
     bye
    1.01
     hi
    1.01
     yes
    1.00
     loudly
    0.99
     sorry
    0.92
    Activations Density 0.130%

    No Known Activations