© 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. 0-RES-JB
    11. 9926
    Prev
    Next
    INDEX
    Explanations

    specific words associated with formal declarations or notices

    oai_token-act-pair · gpt-3.5-turbo

    references to official announcements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ryu
    -0.76
     Leone
    -0.69
     resists
    -0.64
    olen
    -0.64
    slave
    -0.63
     sheltered
    -0.63
     Temper
    -0.62
    false
    -0.61
     penet
    -0.61
    istered
    -0.60
    POSITIVE LOGITS
     announcement
    3.50
     announcements
    2.72
     Announce
    2.09
     announce
    1.93
     announcing
    1.87
     unveiling
    1.77
     announced
    1.65
     proclamation
    1.52
     declaration
    1.43
     announces
    1.42
    Activations Density 0.012%

    No Known Activations