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. 0-RES-JB
    6. 21101
    Prev
    Next
    INDEX
    Explanations

    mentions of the specific newspaper "The Boston Globe"

    oai_token-act-pair · gpt-3.5-turbo

    mentions of "The Globe," primarily as a reference to news articles or reports

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    cks
    -0.82
    ##
    -0.74
    redits
    -0.66
    _(
    -0.65
     \"
    -0.62
    akens
    -0.61
    pper
    -0.60
    agy
    -0.60
     unle
    -0.59
    araoh
    -0.59
    POSITIVE LOGITS
     Globe
    4.33
     Glob
    1.75
     Herald
    1.48
    Gl
    1.25
     globe
    1.21
     Tribune
    1.19
     Province
    1.14
     Newfoundland
    1.08
     CBC
    1.07
     Times
    1.04
    Activations Density 0.010%

    No Known Activations