© 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. 9-RES-JB
    11. 7390
    Prev
    Next
    INDEX
    Explanations

    time periods and historical events

    oai_token-act-pair · gpt-3.5-turbo

    phrases that mention specific time periods or durations related to historical events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    gue
    -0.82
    Ingredients
    -0.79
    Tickets
    -0.70
    mol
    -0.67
    KO
    -0.67
    deck
    -0.65
    CV
    -0.64
    CLA
    -0.62
     converter
    -0.62
     antidote
    -0.62
    POSITIVE LOGITS
     eras
    1.18
     periods
    1.13
     administrations
    1.03
     tumultuous
    0.99
     turbulent
    0.97
     Prohibition
    0.96
     decades
    0.94
     Recession
    0.94
     wartime
    0.93
     WWII
    0.92
    Activations Density 0.209%

    No Known Activations