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. 14187
    Prev
    Next
    INDEX
    Explanations

    mentions of university tuition and fees

    oai_token-act-pair · gpt-3.5-turbo

    terms related to university tuition and fees

    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
    ulf
    -0.72
     Breed
    -0.71
    ï¸ı
    -0.67
     Samar
    -0.65
    orb
    -0.63
     Flavoring
    -0.63
    saf
    -0.62
    quick
    -0.62
    omes
    -0.61
    ometown
    -0.61
    POSITIVE LOGITS
     tuition
    1.16
     fees
    1.01
    ©¶æ¥µ
    0.97
     waivers
    0.90
    uates
    0.83
     dues
    0.83
     reimbursement
    0.82
     costs
    0.79
     scholarships
    0.79
     fee
    0.78
    Activations Density 0.005%

    No Known Activations