© 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. 20536
    Prev
    Next
    INDEX
    Explanations

    references to countries, states, political figures, and government-related topics

    oai_token-act-pair · gpt-3.5-turbo

    mentions of political entities and related organizations

    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
    sed
    -0.71
    urated
    -0.66
    named
    -0.66
    attr
    -0.65
    £ı
    -0.64
    lished
    -0.64
    è£
    -0.62
    _>
    -0.62
    mentioned
    -0.61
    >(
    -0.61
    POSITIVE LOGITS
     needs
    1.40
     should
    1.32
     shouldn
    1.29
     cannot
    1.28
     lacks
    1.28
     deserves
    1.27
     ought
    1.26
     intends
    1.25
     must
    1.21
    needs
    1.16
    Activations Density 0.450%

    No Known Activations