Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & 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. 7-RES-JB
    6. 6531
    Prev
    Next
    INDEX
    Explanations

    days of the week

    oai_token-act-pair · gpt-3.5-turbo

    references to specific days of the week

    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
     Conquer
    -0.70
    arnaev
    -0.68
    pires
    -0.67
    ocate
    -0.64
    insured
    -0.61
    ldon
    -0.61
    ategory
    -0.61
    wer
    -0.60
    laus
    -0.60
     quo
    -0.59
    POSITIVE LOGITS
     afternoon
    1.43
     morning
    1.31
     evening
    1.30
     mornings
    1.23
     night
    1.19
     evenings
    1.10
     nights
    1.01
    morning
    0.94
     heels
    0.84
     Night
    0.84
    Activations Density 0.075%

    No Known Activations