© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 3-RES-JB
    6. 23667
    Prev
    Next
    INDEX
    Explanations

    mentions of time periods

    oai_token-act-pair · gpt-3.5-turbo

    references to the current time period or events happening "this" year, month, or week

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    masters
    -0.74
    76561
    -0.66
    ilitarian
    -0.65
     Papers
    -0.64
    ilus
    -0.64
    agi
    -0.64
    gans
    -0.62
    pots
    -0.62
     laughs
    -0.61
    master
    -0.61
    POSITIVE LOGITS
     week
    1.07
     year
    1.00
     month
    0.98
     morning
    0.93
     afternoon
    0.91
     weekend
    0.87
     semester
    0.85
     particular
    0.81
     latest
    0.81
     incarnation
    0.80
    Activations Density 0.291%

    No Known Activations