© 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. 8-RES-JB
    11. 3222
    Prev
    Next
    INDEX
    Explanations

    time-related indicators, specifically months and years

    oai_token-act-pair · gpt-3.5-turbo

    references to periods of time, specifically months and years

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    anooga
    -0.76
    assium
    -0.70
    owler
    -0.69
    romeda
    -0.69
    ech
    -0.69
    edia
    -0.67
    ITNESS
    -0.66
    reference
    -0.66
    eus
    -0.64
    icator
    -0.64
    POSITIVE LOGITS
     ago
    1.27
     Ago
    1.00
     gestation
    0.90
     undercover
    0.82
     apiece
    0.79
     campaigning
    0.76
     elapsed
    0.75
    long
    0.74
     probation
    0.73
     pregnant
    0.71
    Activations Density 0.147%

    No Known Activations