Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 0-RES-JB
    6. 759
    Prev
    Next
    INDEX
    Explanations

    superlatives related to speed

    oai_token-act-pair · gpt-3.5-turbo

    words related to speed or rapidity

    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
    ë
    -0.65
    hn
    -0.63
    ÃŃn
    -0.63
    eral
    -0.63
    osure
    -0.62
    iol
    -0.61
    sever
    -0.59
    ï
    -0.59
    isle
    -0.58
    cy
    -0.58
    POSITIVE LOGITS
     fastest
    3.69
     quickest
    2.85
     faster
    1.83
     shortest
    1.71
     safest
    1.70
     longest
    1.65
     cheapest
    1.65
     hardest
    1.62
     easiest
    1.57
     tallest
    1.54
    Activations Density 0.007%

    No Known Activations