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. 7501
    Prev
    Next
    INDEX
    Explanations

    information related to the United States, such as data, activities, locations, and specific occurrences happening in the country

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "the."

    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
    ibl
    -0.72
    Iterator
    -0.71
    govtrack
    -0.71
    #$
    -0.70
     partName
    -0.68
    witch
    -0.66
    ÏĢ
    -0.64
     listens
    -0.63
    fn
    -0.62
    \-
    -0.62
    POSITIVE LOGITS
     same
    1.26
     Philippines
    1.11
     latter
    1.07
     latest
    1.02
     United
    1.01
     country
    1.00
     poorest
    1.00
     aforementioned
    0.99
     largest
    0.96
     heaviest
    0.96
    Activations Density 1.055%

    No Known Activations