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

    Neuronpedia

    APICircuit 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. 6-RES-JB
    6. 3492
    Prev
    Next
    INDEX
    Explanations

    keywords related to time intervals like "day" and "week" in combination with the frequency of activities

    oai_token-act-pair · gpt-3.5-turbo

    references to time periods, particularly days, weeks, and their frequencies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    hod
    -0.75
    ibaba
    -0.74
    assies
    -0.73
    raviolet
    -0.72
    enhagen
    -0.68
    erity
    -0.68
    emort
    -0.68
    drawn
    -0.67
    abama
    -0.66
    andals
    -0.66
    POSITIVE LOGITS
     throughout
    0.74
     supplement
    0.69
     basis
    0.67
     thereafter
    0.66
     smoker
    0.66
     istg
    0.64
     relentlessly
    0.62
    ilo
    0.61
     ago
    0.61
    oire
    0.61
    Activations Density 0.050%

    No Known Activations