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. 10-RES-JB
    6. 14843
    Prev
    Next
    INDEX
    Explanations

    phrases related to daily routines or activities

    oai_token-act-pair · gpt-3.5-turbo

    references to daily routines or activities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    essee
    -0.85
    dinand
    -0.82
    egal
    -0.80
    yip
    -0.77
     Eag
    -0.77
    aye
    -0.76
    ename
    -0.74
    emark
    -0.74
    artisan
    -0.74
    boa
    -0.73
    POSITIVE LOGITS
    motion
    1.18
     routines
    1.10
     occurrences
    1.02
     routine
    1.02
     occurrence
    0.97
     necessities
    0.97
     commute
    0.95
     life
    0.94
     chores
    0.90
     tasks
    0.90
    Activations Density 0.045%

    No Known Activations