© 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. 2811
    Prev
    Next
    INDEX
    Explanations

    phrases related to political figures

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

    phrases involving the word "to" and its various forms, indicating intention or actions

    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
    furt
    -0.93
    anooga
    -0.91
    PDATE
    -0.78
    âĹ¼
    -0.71
     Printed
    -0.70
    Redd
    -0.70
     teasp
    -0.70
    atures
    -0.69
    drivers
    -0.68
    vertisement
    -0.68
    POSITIVE LOGITS
     nominate
    1.27
     deport
    1.20
     appoint
    1.19
     veto
    1.18
     pardon
    1.14
     renegoti
    1.13
     dismantle
    1.05
     abolish
    1.03
     rescind
    1.02
     certify
    1.01
    Activations Density 0.191%

    No Known Activations