© 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. 10-RES-JB
    11. 22546
    Prev
    Next
    INDEX
    Explanations

    words related to expressing greetings and condolences

    oai_token-act-pair · gpt-3.5-turbo

    expressions of gratitude and well-wishing in communications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     supposedly
    -0.67
     guiName
    -0.65
    illance
    -0.64
    abulary
    -0.62
     killer
    -0.62
    okin
    -0.60
    duction
    -0.60
     dummy
    -0.60
     Finn
    -0.60
    mob
    -0.59
    POSITIVE LOGITS
     thank
    1.47
     THANK
    1.41
     gratitude
    1.39
     congratulate
    1.29
     grateful
    1.25
     Thank
    1.22
     salute
    1.20
    thank
    1.19
     heartfelt
    1.18
     sincerely
    1.17
    Activations Density 0.305%

    No Known Activations