© 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. 4-RES-JB
    11. 20559
    Prev
    Next
    INDEX
    Explanations

    days of the week

    oai_token-act-pair · gpt-3.5-turbo

    references to specific days of the week, particularly Mondays and Tuesdays

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

    No Comments

    Negative Logits
    orph
    -0.77
    atin
    -0.70
    abet
    -0.69
    chest
    -0.69
    respons
    -0.68
    ps
    -0.67
    ript
    -0.67
    relative
    -0.67
    lessly
    -0.66
    ymm
    -0.65
    POSITIVE LOGITS
     afternoon
    1.33
     evening
    1.23
     morning
    1.22
     mornings
    1.14
     night
    1.10
     evenings
    1.01
     nights
    0.92
     eve
    0.89
     heels
    0.88
     Night
    0.87
    Activations Density 0.071%

    No Known Activations