© 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. 15933
    Prev
    Next
    INDEX
    Explanations

    keywords related to making declarations or announcements

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "declare" and its variations

    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
    RH
    -0.71
    Enlarge
    -0.66
    umbn
    -0.65
    angs
    -0.65
    hov
    -0.65
    dayName
    -0.63
    alez
    -0.63
    ealous
    -0.62
    iere
    -0.62
    tips
    -0.62
    POSITIVE LOGITS
     bankruptcy
    1.13
     unequivocally
    1.02
    phas
    0.98
     victory
    0.98
     allegiance
    0.97
     war
    0.95
     independence
    0.94
     goodbye
    0.94
     unconstitutional
    0.90
     aloud
    0.90
    Activations Density 0.055%

    No Known Activations