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. 3-RES-JB
    6. 11097
    Prev
    Next
    INDEX
    Explanations

    mentions of technology and products, particularly those related to the brand "Has"

    oai_token-act-pair · gpt-3.5-turbo

    the phrase "Has" indicating possession or existence in various 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
     lining
    -0.67
    eering
    -0.61
     takedown
    -0.61
    ãģ«
    -0.59
    ruciating
    -0.59
    aneous
    -0.59
     reel
    -0.58
    OOL
    -0.58
     glove
    -0.56
    allery
    -0.56
    POSITIVE LOGITS
    kell
    1.29
    bro
    1.05
     been
    1.02
     Been
    1.00
    been
    0.94
    sel
    0.89
    fred
    0.88
    linger
    0.86
    sels
    0.86
     undergone
    0.84
    Activations Density 0.035%

    No Known Activations