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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & 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. 4733
    Prev
    Next
    INDEX
    Explanations

    dates related to Fridays

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "Friday."

    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
    Not in Any Lists

    No Comments

    Negative Logits
    ership
    -0.94
    hip
    -0.79
    atche
    -0.79
    aeda
    -0.75
    ports
    -0.73
    vironment
    -0.73
    ymm
    -0.72
    itton
    -0.72
    abet
    -0.70
    colour
    -0.69
    POSITIVE LOGITS
     afternoon
    1.48
     morning
    1.48
     night
    1.35
     evening
    1.29
     mornings
    1.20
     Night
    1.13
     nights
    1.10
     prayers
    0.96
     evenings
    0.95
     twilight
    0.92
    Activations Density 0.022%

    No Known Activations