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. 23413
    Prev
    Next
    INDEX
    Explanations

    instances of the phrase "two years ago" in a text

    oai_token-act-pair · gpt-3.5-turbo

    references to time durations, specifically the phrase "years ago."

    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
     Halls
    -0.67
    ogle
    -0.66
    ople
    -0.66
    ibrary
    -0.65
     toilet
    -0.65
    anooga
    -0.63
    icator
    -0.61
     plun
    -0.60
     subp
    -0.60
    own
    -0.60
    POSITIVE LOGITS
     ago
    1.49
     Ago
    1.24
     apiece
    1.06
     elapsed
    0.88
    iversary
    0.87
    long
    0.87
     olds
    0.85
    izons
    0.79
     overdue
    0.77
     shy
    0.75
    Activations Density 0.123%

    No Known Activations