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. 11-RES-JB
    6. 18031
    Prev
    Next
    INDEX
    Explanations

    words related to everyday life activities and routines

    oai_token-act-pair · gpt-3.5-turbo

    concepts related to everyday life and routine activities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    osponsors
    -0.79
    CVE
    -0.73
    EStream
    -0.70
    maxwell
    -0.66
    interstitial
    -0.65
    ernels
    -0.64
    OIL
    -0.64
    hawks
    -0.64
    ricanes
    -0.64
    flag
    -0.63
    POSITIVE LOGITS
     lives
    1.58
     life
    1.54
     everyday
    1.35
     lifestyles
    1.24
     routines
    1.19
    life
    1.17
     interactions
    1.15
     LIFE
    1.15
     existence
    1.13
     lifestyle
    1.10
    Activations Density 0.383%

    No Known Activations