© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 6-RES-JB
    11. 15023
    Prev
    Next
    INDEX
    Explanations

    phrases containing the word "Wake" at high activations

    oai_token-act-pair · gpt-3.5-turbo

    references to "Wake" or "wake up" calls, often suggesting calls to action or awareness

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    inates
    -0.76
    afort
    -0.73
     Strongh
    -0.70
    ahime
    -0.70
     coord
    -0.69
    venants
    -0.65
    atem
    -0.64
    orsi
    -0.63
     mileage
    -0.61
    onel
    -0.61
    POSITIVE LOGITS
    fulness
    1.21
    mares
    1.03
    wake
    1.02
    mare
    0.98
    up
    0.96
    boarding
    0.91
    gate
    0.90
     Wake
    0.87
    urst
    0.85
    caster
    0.83
    Activations Density 0.012%

    No Known Activations