© 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. 1006
    Prev
    Next
    INDEX
    Explanations

    time-related words or phrases like durations, measurements, and speed

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate time durations and intervals

    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
    hammer
    -0.68
    gging
    -0.68
    irie
    -0.64
    roots
    -0.62
    uph
    -0.62
    orget
    -0.62
    agons
    -0.62
    rim
    -0.61
    iHUD
    -0.61
    lict
    -0.61
    POSITIVE LOGITS
     elapsed
    1.29
     intervals
    0.96
     timer
    0.90
    aneously
    0.89
    ngth
    0.88
     ago
    0.86
     increments
    0.83
     apiece
    0.79
    Cooldown
    0.78
     clip
    0.77
    Activations Density 0.037%

    No Known Activations