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. 12057
    Prev
    Next
    INDEX
    Explanations

    terms related to maintenance activities and tasks

    oai_token-act-pair · gpt-3.5-turbo

    terms related to maintenance

    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
    bern
    -0.76
    verning
    -0.74
    xxxxxxxx
    -0.71
    bold
    -0.70
    unin
    -0.69
    ohydrate
    -0.69
    ologue
    -0.68
    izont
    -0.68
    lins
    -0.67
    itably
    -0.67
    POSITIVE LOGITS
    tenance
    1.26
     maintenance
    1.08
     upkeep
    1.05
    taker
    0.87
     Maintenance
    0.84
     chores
    0.82
     schedules
    0.81
     manag
    0.80
     tasks
    0.79
     regimen
    0.77
    Activations Density 0.017%

    No Known Activations