© 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. 7-RES-JB
    11. 1428
    Prev
    Next
    INDEX
    Explanations

    specific days of the week

    oai_token-act-pair · gpt-3.5-turbo

    references to specific days of the week and time indicators in reports

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    •Day of the Week - Spectral Clustering Experiment

    No Comments

    Negative Logits
    pron
    -0.76
    aunted
    -0.75
     sacrific
    -0.70
    coat
    -0.68
    iator
    -0.67
    ctors
    -0.66
     Conquer
    -0.66
    bred
    -0.66
    ariat
    -0.63
    chief
    -0.61
    POSITIVE LOGITS
     Deadline
    0.80
     Strauss
    0.75
     morning
    0.73
     afternoon
    0.72
    NPR
    0.67
     Newsweek
    0.67
     semester
    0.66
     evening
    0.65
     revealing
    0.65
     deadline
    0.65
    Activations Density 0.157%

    No Known Activations