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. 16708
    Prev
    Next
    INDEX
    Explanations

    comparisons of quantities or actions

    oai_token-act-pair · gpt-3.5-turbo

    phrases that express comparisons or differences in quantities or actions

    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
     Katy
    -0.63
     Miko
    -0.62
     commencement
    -0.62
    susp
    -0.62
     Wear
    -0.61
     Griffin
    -0.57
    ike
    -0.56
     Mou
    -0.56
    Draft
    -0.56
     Christy
    -0.56
    POSITIVE LOGITS
    liest
    0.71
    pees
    0.67
    Downloadha
    0.66
    ibaba
    0.66
     traditionally
    0.65
    hattan
    0.65
    20439
    0.65
    athom
    0.64
     sidx
    0.63
     herself
    0.63
    Activations Density 0.164%

    No Known Activations