© 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. 8-RES-JB
    11. 17858
    Prev
    Next
    INDEX
    Explanations

    expressions of gratitude or thanks

    oai_token-act-pair · gpt-3.5-turbo

    expressions of gratitude and acknowledgment

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    quickShipAvailable
    -0.73
    poses
    -0.69
    conserv
    -0.66
    estyle
    -0.66
    inition
    -0.65
    matter
    -0.65
    anooga
    -0.63
     qualifies
    -0.63
    WARN
    -0.63
    ById
    -0.62
    POSITIVE LOGITS
     everyone
    0.86
     Almighty
    0.84
     whoever
    0.82
     commenter
    0.79
     Carolyn
    0.79
     fellow
    0.78
     anyone
    0.77
     everybody
    0.77
     colleagues
    0.74
     congratulate
    0.70
    Activations Density 0.116%

    No Known Activations