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. 19475
    Prev
    Next
    INDEX
    Explanations

    mentions of specific organizations or groups named "Alliance."

    oai_token-act-pair · gpt-3.5-turbo

    the term "Alliance" in various contexts related to organizations or groups

    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
    agate
    -0.83
    Lago
    -0.75
    oses
    -0.73
    soDeliveryDate
    -0.72
    agar
    -0.71
    gone
    -0.71
    amera
    -0.71
    aptic
    -0.70
    orders
    -0.70
    ochemical
    -0.69
    POSITIVE LOGITS
     Alliance
    1.04
     Franç
    0.92
    naire
    0.86
    venture
    0.75
     Firm
    0.73
    ison
    0.72
     Council
    0.70
     alliance
    0.68
     Coalition
    0.68
     Partnership
    0.67
    Activations Density 0.010%

    No Known Activations