Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 1-RES-JB
    6. 19925
    Prev
    Next
    INDEX
    Explanations

    words related to respiration or breathing

    oai_token-act-pair · gpt-3.5-turbo

    terms related to the act of breathing

    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
    DEF
    -0.75
    IFA
    -0.73
    posted
    -0.70
    fold
    -0.70
    REP
    -0.69
    published
    -0.69
    GE
    -0.68
    via
    -0.67
    MER
    -0.65
    sports
    -0.65
    POSITIVE LOGITS
     breathing
    1.26
     breathe
    1.13
     breat
    0.99
     breaths
    0.91
     cavity
    0.90
    ħĭ
    0.86
     ingred
    0.86
     breathed
    0.86
     nodd
    0.80
     compress
    0.79
    Activations Density 0.008%

    No Known Activations