© 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. 3-RES-JB
    11. 410
    Prev
    Next
    INDEX
    Explanations

    phrases related to breathing and respiratory activities

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "breathing" and its related forms, often in medical or emotional contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    pled
    -0.73
    DEF
    -0.68
    IFA
    -0.68
    fold
    -0.65
    iasis
    -0.65
    HCR
    -0.64
    Wars
    -0.64
    MER
    -0.63
    Mah
    -0.62
     Bundy
    -0.62
    POSITIVE LOGITS
     breathe
    0.97
     breathing
    0.93
     breat
    0.86
     cavity
    0.83
    reath
    0.80
    ħĭ
    0.78
     breathed
    0.77
     underwater
    0.76
    ysis
    0.74
    hops
    0.74
    Activations Density 0.008%

    No Known Activations