© 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. 11-RES-JB
    11. 21318
    Prev
    Next
    INDEX
    Explanations

    phrases related to waking up or being awakened

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "wake" and its variations in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    cer
    -0.78
    inates
    -0.76
    asse
    -0.73
     Forbidden
    -0.72
    ahon
    -0.65
     WATCHED
    -0.62
    regate
    -0.60
     refin
    -0.60
    inances
    -0.60
    tein
    -0.58
    POSITIVE LOGITS
    fulness
    1.22
    mares
    1.21
    up
    1.04
     up
    0.99
    mare
    0.92
    upt
    0.92
    boarding
    0.88
     Up
    0.88
    ups
    0.87
    ful
    0.84
    Activations Density 0.038%

    No Known Activations