© 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. 20565
    Prev
    Next
    INDEX
    Explanations

    phrases describing relationships or interactions

    oai_token-act-pair · gpt-3.5-turbo

    prepositions indicating relationships or positions

    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
    arch
    -0.64
    OV
    -0.63
    zona
    -0.54
     TBA
    -0.54
    addafi
    -0.54
    antly
    -0.53
    hare
    -0.52
    hoff
    -0.52
    apolis
    -0.52
    bucks
    -0.52
    POSITIVE LOGITS
     which
    2.50
    which
    2.03
     Which
    1.79
     whom
    1.65
    Which
    1.62
     whose
    1.46
     whence
    1.44
     wherein
    1.31
    whose
    1.22
     whereby
    1.12
    Activations Density 0.909%

    No Known Activations