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. 11-RES-JB
    6. 17937
    Prev
    Next
    INDEX
    Explanations

    mentions of financial pledges or donations

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to financial pledges and fundraising efforts

    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
     msec
    -0.80
    aspers
    -0.79
     occupant
    -0.75
     Eaton
    -0.72
    gregation
    -0.71
     antid
    -0.70
     Olson
    -0.69
    aq
    -0.68
    cn
    -0.68
     Scalia
    -0.67
    POSITIVE LOGITS
     Kickstarter
    2.05
     backer
    1.82
     backers
    1.78
     crowdfunding
    1.71
    Kick
    1.66
     pledge
    1.60
     pledges
    1.60
     Pledge
    1.59
     Stretch
    1.59
     pledging
    1.47
    Activations Density 0.501%

    No Known Activations