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. 19777
    Prev
    Next
    INDEX
    Explanations

    instances of the name "Ko" in the text

    oai_token-act-pair · gpt-3.5-turbo

    references to a specific individual or entity, likely related to "Ko" as a prominent subject in the document

    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
    Þ
    -0.76
     behavi
    -0.73
    Interstitial
    -0.70
    IDENT
    -0.67
    IAL
    -0.66
    Subject
    -0.64
    icist
    -0.64
    ãĤ¼ãĤ¦ãĤ¹
    -0.64
     à¨
    -0.64
    ãĥ¤
    -0.64
    POSITIVE LOGITS
    ko
    1.26
    zzi
    1.12
    pps
    0.97
    ichi
    0.96
    opa
    0.95
    wu
    0.95
    ppa
    0.94
    zzo
    0.93
    ek
    0.93
    ppy
    0.92
    Activations Density 0.005%

    No Known Activations