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

    Neuronpedia

    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. 10-RES-JB
    11. 7154
    Prev
    Next
    INDEX
    Explanations

    phrases related to supporting journalism through reader contributions

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating reader involvement and support in media contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Awakens
    -0.66
    odon
    -0.64
    gow
    -0.59
     beforehand
    -0.58
    omsday
    -0.58
    ãĥ¯ãĥ³
    -0.57
    ounters
    -0.56
     preced
    -0.56
    imates
    -0.56
    worth
    -0.55
    POSITIVE LOGITS
    interstitial
    0.70
     Shutterstock
    0.70
    conservancy
    0.63
     Editorial
    0.63
     journalism
    0.62
     Spons
    0.60
    ired
    0.59
    athered
    0.58
     Patreon
    0.57
     curated
    0.57
    Activations Density 0.073%

    No Known Activations