© 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. 7-RES-JB
    11. 16709
    Prev
    Next
    INDEX
    Explanations

    mention of a specific place called "Wake."

    oai_token-act-pair · gpt-3.5-turbo

    the term "Wake" and its variations, suggesting a focus on concepts related to awakening or awareness

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    afort
    -0.75
    inates
    -0.74
     princip
    -0.67
     Strongh
    -0.66
     coord
    -0.63
     mileage
    -0.63
    uably
    -0.63
     Mehran
    -0.62
     Bolshevik
    -0.61
    ahime
    -0.61
    POSITIVE LOGITS
    fulness
    1.26
    mare
    1.00
    mares
    0.99
    up
    0.97
    caster
    0.96
    boarding
    0.94
    field
    0.89
    wake
    0.89
    own
    0.88
    gate
    0.88
    Activations Density 0.022%

    No Known Activations