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. 24567
    Prev
    Next
    INDEX
    Explanations

    phrases related to the concept of "sense"

    oai_token-act-pair · gpt-3.5-turbo

    references to "common sense" concepts and discussions related to gun control

    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
     cruc
    -0.75
    ippers
    -0.70
     extrad
    -0.69
     furnace
    -0.66
     banquet
    -0.64
    enburg
    -0.64
     oven
    -0.62
     whirlwind
    -0.61
     fastball
    -0.61
     replay
    -0.61
    POSITIVE LOGITS
     Sense
    4.11
    Sense
    3.44
    sense
    2.79
     Perception
    1.06
     sense
    1.05
     Sens
    1.00
     Kant
    0.94
     Naked
    0.93
     Sharing
    0.91
     Sap
    0.90
    Activations Density 0.024%

    No Known Activations