© 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. 2-RES-JB
    11. 12871
    Prev
    Next
    INDEX
    Explanations

    expressions of gratitude or thankfulness

    oai_token-act-pair · gpt-3.5-turbo

    expressions of gratitude

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    女
    -0.78
     Samoa
    -0.73
    ago
    -0.72
     Hurricanes
    -0.71
     Ultron
    -0.68
     diver
    -0.63
    spir
    -0.61
     detached
    -0.60
     Luxem
    -0.60
     inhabited
    -0.59
    POSITIVE LOGITS
    giving
    1.22
     Thanks
    1.00
    bye
    0.90
     Credits
    0.84
    Thanks
    0.84
    udos
    0.79
     Guys
    0.78
     thanks
    0.77
     pardon
    0.75
    reenshots
    0.74
    Activations Density 0.010%

    No Known Activations