© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 11-RES-JB
    11. 18703
    Prev
    Next
    INDEX
    Explanations

    time durations, specifically focusing on durations of years

    oai_token-act-pair · gpt-3.5-turbo

    references to time durations, particularly in years

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ibrary
    -0.66
    Leaks
    -0.64
    achus
    -0.63
    ople
    -0.62
    eus
    -0.62
     Hearing
    -0.58
    ergic
    -0.57
    ash
    -0.56
    eston
    -0.56
    apo
    -0.55
    POSITIVE LOGITS
     ago
    1.37
     olds
    1.10
     consecut
    1.03
     Ago
    0.96
     apiece
    0.81
     running
    0.81
     old
    0.80
    manship
    0.78
    '
    0.78
    hips
    0.76
    Activations Density 0.118%

    No Known Activations