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. 21354
    Prev
    Next
    INDEX
    Explanations

    phrases related to speed or rate

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to slower speeds or diminished performance

    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
    fit
    -0.72
    redible
    -0.68
    bay
    -0.63
     Answers
    -0.61
     seal
    -0.61
    oup
    -0.60
    har
    -0.60
    Picture
    -0.59
    jet
    -0.57
     Guy
    -0.57
    POSITIVE LOGITS
     slower
    2.92
     weaker
    1.76
     heavier
    1.51
     quieter
    1.47
     shorter
    1.39
     narrower
    1.32
     softer
    1.32
     poorer
    1.31
     colder
    1.25
     smaller
    1.22
    Activations Density 0.019%

    No Known Activations