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. 2696
    Prev
    Next
    INDEX
    Explanations

    words containing the substring "Un"

    oai_token-act-pair · gpt-3.5-turbo

    the term "Un" in various contexts, indicating a focus on a particular entity or organization

    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
    OPLE
    -1.08
    anwhile
    -0.79
    hetti
    -0.77
     Peb
    -0.74
    utical
    -0.74
     Madden
    -0.72
     conduc
    -0.72
     tomat
    -0.71
    Ö¼
    -0.71
    enegger
    -0.71
    POSITIVE LOGITS
    cles
    1.15
    usual
    1.08
    classified
    1.03
    agi
    1.02
    ruly
    1.00
    idad
    1.00
    affiliated
    0.99
    itarian
    0.98
    requ
    0.97
    stable
    0.97
    Activations Density 0.019%

    No Known Activations