© 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. 10-RES-JB
    11. 17289
    Prev
    Next
    INDEX
    Explanations

    phrases indicating a person is occupied or busy

    oai_token-act-pair · gpt-3.5-turbo

    references to the state of being busy or occupied

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    otide
    -0.76
    oi
    -0.66
    IZE
    -0.65
    arium
    -0.64
    INAL
    -0.63
    iste
    -0.62
    Merit
    -0.61
    othermal
    -0.61
    âĵĺ
    -0.60
    ihar
    -0.60
    POSITIVE LOGITS
    work
    0.95
     schedules
    0.91
     juggling
    0.88
    ness
    0.83
     busy
    0.82
    ming
    0.81
    working
    0.80
    bus
    0.80
    cler
    0.79
     schedule
    0.78
    Activations Density 0.044%

    No Known Activations