© 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. 4044
    Prev
    Next
    INDEX
    Explanations

    news and updates related to various topics and events

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

    phrases that indicate significant events or changes in management and leadership

    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
     eleph
    -1.24
     subur
    -0.99
    Þ
    -0.97
     exting
    -0.96
     oun
    -0.95
     pione
    -0.94
     metic
    -0.94
     redes
    -0.91
     conclud
    -0.90
     earthqu
    -0.86
    POSITIVE LOGITS
    Welcome
    1.06
    Reviewed
    1.06
    Introduction
    1.03
    Reviewer
    1.03
    WASHINGTON
    1.03
    Join
    1.01
    Enlarge
    1.01
    Hello
    1.01
    Synopsis
    1.01
    Description
    1.00
    Activations Density 1.227%

    No Known Activations