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

    Neuronpedia

    Jacobian LensNEW
    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. 7473
    Prev
    Next
    INDEX
    Explanations

    phrases or mentions related to charitable donations or fundraising

    oai_token-act-pair · gpt-3.5-turbo

    references to donations or charitable contributions

    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
     brut
    -0.74
    âĶģ
    -0.74
    fecture
    -0.73
    sbm
    -0.72
    verages
    -0.70
     jargon
    -0.70
    skirts
    -0.69
    urated
    -0.68
    assian
    -0.68
    bole
    -0.68
    POSITIVE LOGITS
     charity
    1.40
     charities
    1.40
     scholarships
    1.22
     needy
    1.21
     charitable
    1.17
     orphans
    1.13
     Charity
    1.11
     deserving
    1.03
    ukemia
    1.01
     Cancer
    1.00
    Activations Density 0.276%

    No Known Activations