© 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. 18798
    Prev
    Next
    INDEX
    Explanations

    expressions of thanks, requests, and intentions to do or achieve something

    oai_token-act-pair · gpt-3.5-turbo

    expressions of gratitude and requests

    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
    glers
    -0.64
    MpServer
    -0.64
    furt
    -0.63
    ories
    -0.62
     Emerson
    -0.60
    naires
    -0.60
     tolerated
    -0.59
    apps
    -0.59
    angering
    -0.58
    existence
    -0.58
    POSITIVE LOGITS
     reiterate
    1.57
     congratulate
    1.51
     clarify
    1.50
     thank
    1.50
     apologize
    1.45
     apologise
    1.44
     remind
    1.41
     emphasize
    1.38
     warn
    1.29
     reassure
    1.23
    Activations Density 0.101%

    No Known Activations