© 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. 24515
    Prev
    Next
    INDEX
    Explanations

    phrases expressing gratitude or seeking feedback

    oai_token-act-pair · gpt-3.5-turbo

    expressions of gratitude and requests for feedback

    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
    î
    -0.70
    Shape
    -0.68
    Accessory
    -0.66
    "[
    -0.63
    np
    -0.62
     characterization
    -0.62
     disparate
    -0.62
    enum
    -0.60
    ni
    -0.60
    Huh
    -0.59
    POSITIVE LOGITS
     grate
    1.24
     appreciate
    1.17
     encourage
    1.13
     apologize
    1.10
     THANK
    1.05
     sincerely
    1.05
     apologise
    1.04
     hope
    1.02
     greatly
    0.99
     kindly
    0.98
    Activations Density 0.199%

    No Known Activations