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. 10-RES-JB
    6. 22015
    Prev
    Next
    INDEX
    Explanations

    phrases indicating preparedness or getting ready for a specific situation

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to preparation or readiness for various situations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ware
    -0.75
    æ©Ł
    -0.67
    PDF
    -0.63
    weed
    -0.62
     Originally
    -0.61
    kernel
    -0.61
    WARN
    -0.59
    <?
    -0.59
     incidentally
    -0.58
    hai
    -0.58
    POSITIVE LOGITS
     adulthood
    0.93
     takeoff
    0.93
     emergencies
    0.91
     tomorrow
    0.90
     greatness
    0.90
     eventual
    0.89
     Armageddon
    0.87
     future
    0.86
     impending
    0.84
     battle
    0.84
    Activations Density 0.163%

    No Known Activations