© 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. 13242
    Prev
    Next
    INDEX
    Explanations

    phrases related to giving credit or acknowledgment to someone or something

    oai_token-act-pair · gpt-3.5-turbo

    expressions of gratitude or acknowledgment

    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
     Median
    -0.61
    riage
    -0.56
    viol
    -0.55
    mania
    -0.55
     Closing
    -0.55
     deviation
    -0.53
    chio
    -0.52
     boundary
    -0.52
    verages
    -0.52
     Rebell
    -0.50
    POSITIVE LOGITS
    giving
    1.15
     largely
    0.94
     to
    0.89
     mainly
    0.82
     partly
    0.81
     chiefly
    0.75
     mostly
    0.74
     primarily
    0.72
     thankfully
    0.71
    cription
    0.63
    Activations Density 0.027%

    No Known Activations