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. 6-RES-JB
    6. 4910
    Prev
    Next
    INDEX
    Explanations

    phrases related to swallowing objects or pills

    oai_token-act-pair · gpt-3.5-turbo

    terms related to the act of swallowing

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Chron
    -0.68
    CTV
    -0.67
     Templar
    -0.61
     Templ
    -0.61
    abouts
    -0.61
    nesota
    -0.60
     Sharif
    -0.58
    orem
    -0.58
     Mous
    -0.58
    ements
    -0.57
    POSITIVE LOGITS
     swallowing
    0.90
     swallow
    0.84
     Snape
    0.83
    stakes
    0.82
     gum
    0.81
     inh
    0.81
    ipes
    0.76
    unia
    0.76
    ortium
    0.74
    aneers
    0.74
    Activations Density 0.034%

    No Known Activations