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. 5-RES-JB
    6. 15165
    Prev
    Next
    INDEX
    Explanations

    phrases related to baseball leagues

    oai_token-act-pair · gpt-3.5-turbo

    references to the term "Triple," specifically in the context of sports and performance metrics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    sbm
    -0.83
    swer
    -0.81
    ORE
    -0.77
    INESS
    -0.71
    eared
    -0.71
    earing
    -0.70
    7601
    -0.70
    ä½ľ
    -0.68
    anse
    -0.68
    enegger
    -0.67
    POSITIVE LOGITS
    plet
    0.93
    teen
    0.92
    plets
    0.92
     digits
    0.81
    ty
    0.78
    leaf
    0.75
    header
    0.72
     digit
    0.70
    ulic
    0.69
     submer
    0.68
    Activations Density 0.012%

    No Known Activations