© 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. 773
    Prev
    Next
    INDEX
    Explanations

    phrases related to awakening or realizing something

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "woke" and its variations related to awakening

    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
    -0.82
    esan
    -0.74
    regate
    -0.71
    inate
    -0.69
    ietal
    -0.68
    entric
    -0.67
     Britann
    -0.65
    onne
    -0.65
    orously
    -0.64
    adr
    -0.63
    POSITIVE LOGITS
    mares
    1.14
    wake
    0.98
     refreshed
    0.92
     awake
    0.91
     awaken
    0.84
     woke
    0.83
     awoke
    0.81
    mare
    0.77
    leep
    0.77
     wakes
    0.73
    Activations Density 0.029%

    No Known Activations