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. 8-RES-JB
    6. 4518
    Prev
    Next
    INDEX
    Explanations

    time markers and transition phrases

    oai_token-act-pair · gpt-3.5-turbo

    temporal phrases indicating specific times or moments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ®
    -0.67
     globally
    -0.64
     Historically
    -0.64
     promotes
    -0.63
     Founders
    -0.63
     hosted
    -0.62
     esports
    -0.61
    /$
    -0.61
     Americas
    -0.61
     Tradable
    -0.60
    POSITIVE LOGITS
    upon
    1.02
    Later
    0.99
    Soon
    0.95
     ensuing
    0.94
    uddenly
    0.91
    stairs
    0.91
    neath
    0.89
    sequently
    0.89
    Suddenly
    0.88
     thereafter
    0.86
    Activations Density 0.407%

    No Known Activations