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. 1-RES-JB
    6. 23441
    Prev
    Next
    INDEX
    Explanations

    text related to educational institutions named "academy"

    oai_token-act-pair · gpt-3.5-turbo

    references to educational or training institutions, especially those described as academies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Bundy
    -0.71
    pull
    -0.70
    olls
    -0.70
    ï¸ı
    -0.69
    evil
    -0.66
    â̳
    -0.65
    ter
    -0.64
     Individuals
    -0.63
    ests
    -0.63
    gets
    -0.63
    POSITIVE LOGITS
     academy
    1.31
     acad
    1.00
     curriculum
    0.79
     corps
    0.77
    smanship
    0.75
     Academy
    0.73
     millenn
    0.73
    æ©
    0.72
    emies
    0.72
     graduates
    0.72
    Activations Density 0.009%

    No Known Activations