© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 8-RES-JB
    11. 3270
    Prev
    Next
    INDEX
    Explanations

    details about daily routines and activities, such as eating, exercising, and working

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to daily routines and family life

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     attribution
    -0.83
    entity
    -0.81
    worthiness
    -0.81
     likeness
    -0.80
    bold
    -0.77
     legitimacy
    -0.76
     licens
    -0.74
     endors
    -0.74
     derivative
    -0.73
     eminent
    -0.73
    POSITIVE LOGITS
     mornings
    1.38
     evenings
    1.36
     weekends
    1.21
     waking
    1.18
     snacks
    1.18
     wakes
    1.15
     meals
    1.14
     nights
    1.13
     vacations
    1.13
     Sundays
    1.12
    Activations Density 1.231%

    No Known Activations