© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 24501
    Prev
    Next
    INDEX
    Explanations

    expressions of gratitude or thanks

    oai_token-act-pair · gpt-3.5-turbo

    phrases expressing gratitude or thanks

    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
    furt
    -0.69
    glers
    -0.66
    ories
    -0.65
    earch
    -0.64
    fighting
    -0.61
    MpServer
    -0.60
     Mayhem
    -0.58
     dominates
    -0.58
    ById
    -0.57
     Emerson
    -0.57
    POSITIVE LOGITS
     thank
    1.51
     congratulate
    1.44
     reiterate
    1.38
     apologize
    1.35
     apologise
    1.35
     THANK
    1.29
     clarify
    1.27
     commend
    1.26
     emphasize
    1.22
     sincerely
    1.20
    Activations Density 0.080%

    No Known Activations