© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 11-RES-JB
    6. 12260
    Prev
    Next
    INDEX
    Explanations

    direct speech quotations with an emotional intensity

    oai_token-act-pair · gpt-3.5-turbo

    punctuation indicating speech or quotation

    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
    rats
    -0.88
    DragonMagazine
    -0.87
    ãĥij
    -0.86
    NetMessage
    -0.85
    £ı
    -0.78
    brids
    -0.74
    meric
    -0.73
    EStreamFrame
    -0.73
    catentry
    -0.72
    haar
    -0.71
    POSITIVE LOGITS
     said
    1.36
     remarked
    1.25
    said
    1.25
     wrote
    1.24
     exclaimed
    1.22
     commented
    1.19
     tweeted
    1.19
     joked
    1.17
     reads
    1.15
     says
    1.14
    Activations Density 0.106%

    No Known Activations