© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 11-RES-JB
    11. 7609
    Prev
    Next
    INDEX
    Explanations

    links to geographic locations and political events

    oai_token-act-pair · gpt-3.5-turbo

    specific terms related to social, political, and economic issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    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
     or
    -0.58
    jab
    -0.58
    ipeg
    -0.55
     nor
    -0.55
    gyn
    -0.53
    ibrary
    -0.53
    tif
    -0.52
    ozyg
    -0.52
     âĸº
    -0.52
    Cop
    -0.52
    POSITIVE LOGITS
     thereof
    1.06
     alike
    1.00
     are
    0.91
     complicate
    0.91
     attest
    0.91
     thereto
    0.91
     underscore
    0.88
     abound
    0.87
     remain
    0.86
     were
    0.86
    Activations Density 0.508%

    No Known Activations