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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 6-RES-JB
    11. 9300
    Prev
    Next
    INDEX
    Explanations

    mentions of the weekday "Wednesday."

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the day "Wednesday."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    åĬ
    -0.86
    abet
    -0.76
    pend
    -0.75
    iful
    -0.74
    chest
    -0.74
    Export
    -0.72
    orius
    -0.71
    ebook
    -0.70
    friends
    -0.70
    buffer
    -0.68
    POSITIVE LOGITS
     morning
    1.46
     afternoon
    1.42
     evening
    1.34
     night
    1.33
     mornings
    1.14
     nights
    1.11
     evenings
    1.08
    morning
    1.05
    nesday
    0.95
     Morning
    0.93
    Activations Density 0.027%

    No Known Activations