© 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. 10-RES-JB
    11. 7056
    Prev
    Next
    INDEX
    Explanations

    verbs related to decision-making and announcements

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to making decisions or taking actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Niet
    -0.77
    bour
    -0.73
     exceeded
    -0.69
     grinning
    -0.69
    gypt
    -0.65
     outper
    -0.63
    Mania
    -0.61
     wit
    -0.59
     laughed
    -0.58
    strip
    -0.58
    POSITIVE LOGITS
     decisions
    1.30
     adjustments
    1.25
     arrangements
    1.12
     judgments
    1.11
     inquiries
    1.08
     recommendations
    1.03
     announcements
    1.03
     determin
    1.02
     changes
    1.02
     concessions
    1.02
    Activations Density 0.105%

    No Known Activations