© 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. 11-RES-JB
    11. 7869
    Prev
    Next
    INDEX
    Explanations

    declarations or statements of significance

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "declare" in various forms

    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
    ographers
    -0.76
     partName
    -0.75
    ograp
    -0.71
    ographer
    -0.71
    alez
    -0.66
    ographical
    -0.66
    RH
    -0.64
    umbn
    -0.64
    aptic
    -0.63
    WARE
    -0.63
    POSITIVE LOGITS
     bankruptcy
    1.22
     oneself
    1.02
     allegiance
    1.01
     war
    1.01
     victory
    1.00
     independence
    0.99
     martial
    0.97
     himself
    0.91
     herself
    0.91
     unequivocally
    0.90
    Activations Density 0.056%

    No Known Activations