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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 4669
    Prev
    Next
    INDEX
    Explanations

    mentions of tips or advice

    oai_token-act-pair · gpt-3.5-turbo

    references to "tips" or advice

    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
    owicz
    -0.73
     Abstract
    -0.67
    sych
    -0.65
    rac
    -0.64
    aign
    -0.64
    Abstract
    -0.64
    omics
    -0.64
    orians
    -0.63
    managed
    -0.62
    ships
    -0.61
    POSITIVE LOGITS
     tip
    4.13
    tip
    2.78
     Tip
    2.56
     tips
    2.50
    Tip
    2.30
    tips
    2.10
     tipped
    2.07
     tipping
    1.78
     Tips
    1.67
    Tips
    1.57
    Activations Density 0.018%

    No Known Activations