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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 2404
    Prev
    Next
    INDEX
    Explanations

    the word "Fast" with various numerical values following it, suggesting a focus on speed or quickness

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the "Fast and Furious" franchise

    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
     Albion
    -0.73
    oral
    -0.68
    ogyn
    -0.66
     tou
    -0.66
     depression
    -0.64
     outlook
    -0.63
     psychiat
    -0.61
     depressive
    -0.60
     Rae
    -0.60
     subord
    -0.59
    POSITIVE LOGITS
     Fast
    3.76
    Fast
    3.40
    fast
    2.28
     fast
    1.99
     Faster
    1.55
     Furious
    1.48
     Slow
    1.46
     fastest
    1.24
     Quick
    1.22
     Speed
    1.19
    Activations Density 0.011%

    No Known Activations