Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 3-RES-JB
    6. 7939
    Prev
    Next
    INDEX
    Explanations

    mentions of specific units of time like "day," "week," or "year."

    oai_token-act-pair · gpt-3.5-turbo

    references to the frequency of occurrences related to time, specifically "day" and "year."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ounded
    -0.75
    jri
    -0.72
    aucuses
    -0.71
    itative
    -0.68
     beginnings
    -0.67
     discour
    -0.67
    gars
    -0.66
    wolves
    -0.64
    arty
    -0.62
    ÃĥÃĤ
    -0.62
    POSITIVE LOGITS
     imaginable
    0.89
     thereafter
    0.82
     whatsoever
    0.74
     consecut
    0.71
     except
    0.70
    night
    0.69
    adelphia
    0.69
    inery
    0.67
    soever
    0.67
    Downloadha
    0.67
    Activations Density 0.059%

    No Known Activations