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. 3305
    Prev
    Next
    INDEX
    Explanations

    phrases related to engaging or targeting audiences

    oai_token-act-pair · gpt-3.5-turbo

    mentions of audiences and their engagement with content

    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
    run
    -0.67
     accessory
    -0.66
     item
    -0.66
     OPT
    -0.65
     tree
    -0.63
     Item
    -0.62
    osa
    -0.61
    lb
    -0.61
     appendix
    -0.61
    du
    -0.61
    POSITIVE LOGITS
     audiences
    3.66
     viewers
    1.81
     listeners
    1.55
     crowds
    1.45
     readers
    1.39
     constituencies
    1.31
     studios
    1.30
     audience
    1.28
    goers
    1.27
     populations
    1.27
    Activations Density 0.014%

    No Known Activations