© 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. 0-RES-JB
    11. 7860
    Prev
    Next
    INDEX
    Explanations

    comparative adjectives denoting speed

    oai_token-act-pair · gpt-3.5-turbo

    multiple instances of the word "faster" and its synonyms, indicating speed or efficiency

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Orig
    -0.65
    occup
    -0.64
    otal
    -0.63
     fig
    -0.63
    fell
    -0.63
     Orig
    -0.63
     Villa
    -0.62
    Occup
    -0.61
     Dwell
    -0.61
     Plum
    -0.61
    POSITIVE LOGITS
     faster
    3.55
     quicker
    2.94
     slower
    2.71
     Faster
    2.26
     fastest
    2.12
     fast
    1.84
     smoother
    1.82
     quickest
    1.76
     smarter
    1.72
     sooner
    1.59
    Activations Density 0.018%

    No Known Activations