© 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. 11482
    Prev
    Next
    INDEX
    Explanations

    expressions related to recognition, appreciation, contributions, and actions made by individuals towards others

    oai_token-act-pair · gpt-3.5-turbo

    expressions of gratitude and acknowledgment of contributions

    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
    pmwiki
    -0.82
    ļéĨĴ
    -0.71
    avoid
    -0.71
    govtrack
    -0.70
    ptive
    -0.68
    neutral
    -0.66
    Newsletter
    -0.66
     Reported
    -0.64
     Asked
    -0.64
    atis
    -0.64
    POSITIVE LOGITS
     tremendous
    1.31
     invaluable
    1.27
     incredible
    1.20
     countless
    1.16
     amazing
    1.12
     alot
    1.10
     unbelievable
    1.10
     immense
    1.09
     enormous
    1.03
     tremendously
    1.02
    Activations Density 0.419%

    No Known Activations