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. 22845
    Prev
    Next
    INDEX
    Explanations

    phrases related to government shutdowns

    oai_token-act-pair · gpt-3.5-turbo

    references to government shutdowns

    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
    Lev
    -0.76
    uana
    -0.76
    oeuv
    -0.73
    eva
    -0.73
    haps
    -0.72
    ---------------
    -0.69
    DN
    -0.68
    OGR
    -0.67
    Digital
    -0.66
    OD
    -0.66
    POSITIVE LOGITS
     shutdown
    1.00
     aver
    0.88
     Shutdown
    0.88
    ascus
    0.79
     showdown
    0.71
     defund
    0.68
     standoff
    0.68
     prevention
    0.67
     zone
    0.67
    aby
    0.67
    Activations Density 0.012%

    No Known Activations