© 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. 11-RES-JB
    11. 20906
    Prev
    Next
    INDEX
    Explanations

    religious terms or references

    oai_token-act-pair · gpt-3.5-turbo

    references to relatives or family relationships

    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
     wide
    -0.71
     Lead
    -0.65
     wider
    -0.60
     thinly
    -0.60
     Slate
    -0.60
     slate
    -0.59
     buck
    -0.59
     Marketplace
    -0.57
     Wilde
    -0.57
     Swan
    -0.56
    POSITIVE LOGITS
    igion
    1.70
    iability
    1.50
    iable
    1.47
    atively
    1.42
    igious
    1.39
    atives
    1.36
    iever
    1.36
    iance
    1.35
    ativity
    1.33
    aunch
    1.33
    Activations Density 0.029%

    No Known Activations