© 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. 16001
    Prev
    Next
    INDEX
    Explanations

    verbs that describe interactions or relationships with other individuals or groups

    oai_token-act-pair · gpt-3.5-turbo

    actions and behaviors relevant to significant personal and historical events

    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
    halla
    -0.97
    Supplement
    -0.74
    \.
    -0.72
    WARE
    -0.71
    buster
    -0.70
    ItemThumbnailImage
    -0.68
    they
    -0.67
    padding
    -0.66
    Split
    -0.65
    hazard
    -0.64
    POSITIVE LOGITS
     fellow
    1.03
     opponents
    0.95
     passers
    0.92
     foes
    0.86
     opponent
    0.82
     Adolf
    0.79
     enemies
    0.78
     adversaries
    0.78
     unsuspecting
    0.77
     numerous
    0.77
    Activations Density 0.692%

    No Known Activations