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. 17349
    Prev
    Next
    INDEX
    Explanations

    financial figures or data such as monetary amounts

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of "rest" or related themes of restfulness

    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
    ixel
    -0.72
    acious
    -0.70
    acular
    -0.69
     incendiary
    -0.68
     latex
    -0.67
    undy
    -0.64
    ucci
    -0.63
     mathemat
    -0.63
     mathematician
    -0.62
    Leaks
    -0.62
    POSITIVE LOGITS
    Rest
    2.99
     Rest
    2.37
     resting
    2.34
    rest
    1.34
     Restore
    1.33
     REST
    1.31
     RIP
    1.25
     rest
    1.16
     Subst
    1.10
     Fare
    1.09
    Activations Density 0.026%

    No Known Activations