© 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. 12298
    Prev
    Next
    INDEX
    Explanations

    negative sentiments and criticisms

    oai_token-act-pair · gpt-3.5-turbo

    phrases expressing frustration or disappointment

    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
     Refugees
    -0.55
     Niño
    -0.49
     Ney
    -0.48
     Bulgar
    -0.48
     Reincarn
    -0.47
     Dalai
    -0.47
     Guests
    -0.47
     eleph
    -0.47
     Emblem
    -0.46
     Nutr
    -0.45
    POSITIVE LOGITS
    ebin
    0.52
    .).
    0.51
    .'"
    0.49
     whence
    0.47
    ipped
    0.47
    !--
    0.47
    ascript
    0.47
    !'"
    0.47
    .—
    0.47
    .
    0.46
    Activations Density 0.991%

    No Known Activations