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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 2-RES-JB
    11. 364
    Prev
    Next
    INDEX
    Explanations

    instances of the past tense of "wake," specifically the word "woke"

    oai_token-act-pair · gpt-4-turbo

    references to waking up or awakening

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "woke" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    inates
    -0.82
    onne
    -0.78
    orde
    -0.70
     Hezbollah
    -0.70
    iyah
    -0.66
     collateral
    -0.65
    ateral
    -0.64
    ately
    -0.64
    asse
    -0.64
    osa
    -0.63
    POSITIVE LOGITS
    mares
    1.21
    wake
    1.12
     woke
    0.90
     awake
    0.85
    dream
    0.83
     wakes
    0.79
     wake
    0.77
    Dream
    0.76
    leep
    0.76
    achine
    0.75
    Activations Density 0.015%

    No Known Activations