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. 10-RES-JB
    6. 1523
    Prev
    Next
    INDEX
    Explanations

    words related to breathing and inhaling

    oai_token-act-pair · gpt-3.5-turbo

    terms related to inhalation and exhalation processes

    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
     Tycoon
    -0.65
     sarc
    -0.62
     Leap
    -0.61
     Hels
    -0.60
    minus
    -0.60
    Hill
    -0.59
    tsky
    -0.59
    HOU
    -0.59
     Seraph
    -0.58
     Marble
    -0.58
    POSITIVE LOGITS
    ospital
    1.30
    aled
    1.22
    osp
    1.07
    aling
    1.05
    ogen
    0.95
    ogens
    0.95
    uming
    0.94
    omed
    0.89
    avored
    0.88
    ales
    0.88
    Activations Density 0.035%

    No Known Activations