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. 0-RES-JB
    6. 10617
    Prev
    Next
    INDEX
    Explanations

    topics related to publicity and promotions

    oai_token-act-pair · gpt-3.5-turbo

    terms associated with publicity

    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
    alian
    -0.67
    amber
    -0.67
    olor
    -0.64
    cients
    -0.63
     Balanced
    -0.63
    CENT
    -0.63
    estamp
    -0.61
    pes
    -0.60
     Elements
    -0.60
    ores
    -0.60
    POSITIVE LOGITS
     publicity
    3.77
     notoriety
    1.68
     promotional
    1.40
     fame
    1.37
     publicized
    1.31
     attention
    1.23
     hype
    1.17
     marketing
    1.16
     secrecy
    1.16
     advertising
    1.16
    Activations Density 0.012%

    No Known Activations