© 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. 11-RES-JB
    11. 5079
    Prev
    Next
    INDEX
    Explanations

    references to Kickstarter campaigns

    oai_token-act-pair · gpt-3.5-turbo

    references to Kickstarter campaigns and related terminology

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Scalia
    -0.76
    aspers
    -0.74
    ropolitan
    -0.72
    otom
    -0.72
    obar
    -0.68
    amber
    -0.66
    gregation
    -0.66
    idents
    -0.66
    obe
    -0.64
    bars
    -0.64
    POSITIVE LOGITS
     crowdfunding
    1.10
     backers
    1.09
     campaigns
    1.08
     campaign
    1.08
     Campaign
    1.03
     backer
    1.02
     Kickstarter
    1.00
     fundraising
    0.96
    Kick
    0.96
    funding
    0.95
    Activations Density 0.067%

    No Known Activations