© 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 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. 10715
    Prev
    Next
    INDEX
    Explanations

    dates and time periods

    oai_token-act-pair · gpt-3.5-turbo

    specific time-related expressions and dates

    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
     flyers
    -0.72
     shout
    -0.70
     discrim
    -0.67
     nets
    -0.65
    ãĥ³ãĤ¸
    -0.63
     magnet
    -0.63
     stret
    -0.62
     gorilla
    -0.59
    asive
    -0.59
     privately
    -0.59
    POSITIVE LOGITS
     adulthood
    1.33
     2025
    1.09
     infancy
    1.07
     expiration
    1.05
    ruary
    1.03
     2030
    1.00
     adolescence
    1.00
    FontSize
    0.98
     2021
    0.98
    Sept
    0.98
    Activations Density 0.884%

    No Known Activations