© 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 EvalsExportsinterp-engineNEWAPI 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. 12-RES-JB
    11. 2719
    Prev
    Next
    INDEX
    Explanations

    phrases related to societal issues and cultural contexts

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot

    phrases related to societal issues and the American context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 12-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.hook_resid_post
    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_post
    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
    NetMessage
    -0.76
    etsk
    -0.75
    seekers
    -0.75
    ilee
    -0.72
    POSE
    -0.72
    ignty
    -0.71
    nil
    -0.71
    pas
    -0.71
    heed
    -0.71
    peat
    -0.71
    POSITIVE LOGITS
     workplace
    1.07
     United
    1.00
     halls
    0.99
     humanities
    0.99
     corridors
    0.98
     realm
    0.95
     minds
    0.94
     media
    0.93
     West
    0.92
     wake
    0.92
    Activations Density 0.227%

    No Known Activations