© 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. 1-RES-JB
    11. 15696
    Prev
    Next
    INDEX
    Explanations

    references to a specific name "Boo" with varying degrees of emphasis

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the name "Boo" and variations of "oops" along with expressions of surprise or exclamation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    士
    -0.80
     Vessel
    -0.79
    auder
    -0.75
     Prometheus
    -0.72
    pring
    -0.69
    places
    -0.68
    tor
    -0.68
    son
    -0.66
     narratives
    -0.65
    place
    -0.64
    POSITIVE LOGITS
    Boo
    1.14
    ooo
    1.04
     Hoo
    0.93
    oot
    0.89
     Oo
    0.87
    hedon
    0.87
     Boo
    0.85
    ogle
    0.84
    oooo
    0.83
    *=-
    0.82
    Activations Density 0.014%

    No Known Activations