© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 0-RES-JB
    11. 12559
    Prev
    Next
    INDEX
    Explanations

    phrases related to promotional activities or costs

    oai_token-act-pair · gpt-3.5-turbo

    references to promotional items and activities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     bis
    -0.71
    rees
    -0.71
    deep
    -0.69
    >[
    -0.66
    Nik
    -0.66
    aleb
    -0.66
     Nare
    -0.65
    .–
    -0.64
    dar
    -0.64
    xit
    -0.64
    POSITIVE LOGITS
     promotional
    3.57
     promo
    2.38
     promotions
    1.89
     promotion
    1.81
     marketing
    1.69
     publicity
    1.50
     introductory
    1.42
     teaser
    1.39
     Promotion
    1.37
     promot
    1.27
    Activations Density 0.017%

    No Known Activations