© 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. 9-RES-JB
    11. 18079
    Prev
    Next
    INDEX
    Explanations

    time-related phrases related to specific durations: months, years, and decades

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating the passage of time or duration

    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
    wealth
    -0.73
     Cosponsors
    -0.69
    imir
    -0.69
    Fac
    -0.66
    ice
    -0.66
    cause
    -0.65
    este
    -0.62
    BOOK
    -0.62
    tainment
    -0.62
    asma
    -0.61
    POSITIVE LOGITS
     hiatus
    1.01
     absence
    0.76
    ynthesis
    0.76
    dding
    0.74
     deliber
    0.73
     gestation
    0.73
     exhausting
    0.72
     searching
    0.72
     of
    0.72
     slog
    0.71
    Activations Density 0.076%

    No Known Activations