© 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. 20692
    Prev
    Next
    INDEX
    Explanations

    content related to news articles or headlines

    oai_token-act-pair · gpt-3.5-turbo

    commands related to enlarging or toggling images

    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
    warm
    -0.65
    naires
    -0.65
    angering
    -0.62
    angers
    -0.62
    nuts
    -0.62
    anger
    -0.62
    onew
    -0.61
     upt
    -0.60
    comes
    -0.60
     sucker
    -0.60
    POSITIVE LOGITS
    Enlarge
    0.94
    ONSORED
    0.92
    UTERS
    0.85
     Image
    0.85
     WATCHED
    0.85
     caption
    0.79
     toggle
    0.73
     PHOTO
    0.73
     Photo
    0.71
     Reached
    0.69
    Activations Density 0.011%

    No Known Activations