Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APISteerSAE EvalsBlog/PodcastNEWSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    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. 21119
    Prev
    Next
    INDEX
    Explanations

    mentions of charitable activities and organizations

    oai_token-act-pair · gpt-3.5-turbo

    references to charity and charitable organizations

    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
     Snapdragon
    -0.73
     senses
    -0.68
     Detected
    -0.67
    inski
    -0.67
    augh
    -0.66
    Sensor
    -0.66
    bolt
    -0.65
     Teg
    -0.65
     Dong
    -0.65
     Lank
    -0.65
    POSITIVE LOGITS
     charity
    3.89
     charities
    2.89
     Charity
    2.71
     charitable
    2.26
     philanthrop
    1.88
     nonprofits
    1.46
     nonprofit
    1.45
     NGO
    1.42
     fundraiser
    1.40
     fundraising
    1.33
    Activations Density 0.017%

    No Known Activations