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. 13190
    Prev
    Next
    INDEX
    Explanations

    phrases relating to waking up and morning routines

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to waking up or the concept of awakening

    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
    inates
    -0.70
     Proposition
    -0.65
    asse
    -0.64
    cer
    -0.64
     Forbidden
    -0.64
    ahon
    -0.62
     DEFENSE
    -0.61
     refin
    -0.60
    esan
    -0.60
    berus
    -0.58
    POSITIVE LOGITS
    mares
    1.25
    fulness
    1.07
     up
    1.00
    up
    0.96
    mare
    0.93
     refreshed
    0.93
     awake
    0.89
    ups
    0.87
    upt
    0.85
    leep
    0.83
    Activations Density 0.037%

    No Known Activations