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. 18227
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "yesterday"

    oai_token-act-pair · gpt-3.5-turbo

    references to the word "yesterday."

    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
    eers
    -0.94
    eer
    -0.92
    ordes
    -0.78
     Conquer
    -0.77
    iframe
    -0.75
    OHN
    -0.73
    laus
    -0.70
    ophers
    -0.69
    hma
    -0.67
    Loop
    -0.67
    POSITIVE LOGITS
     afternoon
    1.39
     morning
    1.34
     evening
    1.27
     mornings
    1.09
     night
    1.08
     Evening
    0.88
    morning
    0.82
     Night
    0.81
    night
    0.80
     yesterday
    0.78
    Activations Density 0.009%

    No Known Activations