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. 3-RES-JB
    6. 19767
    Prev
    Next
    INDEX
    Explanations

    mentions of school personnel, especially principals

    oai_token-act-pair · gpt-3.5-turbo

    references to school principals and their roles in educational settings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    orne
    -0.82
    rawdownloadcloneembedreportprint
    -0.78
    utral
    -0.77
    issan
    -0.77
    odon
    -0.72
    SHIP
    -0.67
    sonian
    -0.66
     jaw
    -0.64
     limb
    -0.63
    ortium
    -0.62
    POSITIVE LOGITS
    girls
    1.09
    children
    0.97
     Superintendent
    0.96
     Teachers
    0.89
    Kids
    0.89
    chool
    0.81
    masters
    0.76
    Children
    0.76
    kids
    0.75
    boards
    0.72
    Activations Density 0.170%

    No Known Activations