© 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. 10-RES-JB
    11. 16702
    Prev
    Next
    INDEX
    Explanations

    conjunctions connecting time periods

    oai_token-act-pair · gpt-3.5-turbo

    instances and phrases indicating the passage of time or specific temporal periods

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ONSORED
    -0.70
     Cosponsors
    -0.65
    ":""},{"
    -0.61
    ipes
    -0.61
     condu
    -0.60
     enthusi
    -0.59
     coordin
    -0.57
    semb
    -0.57
     Toro
    -0.57
    ãĥķãĤ©
    -0.57
    POSITIVE LOGITS
    night
    1.05
     moon
    0.95
     night
    0.93
    day
    0.87
     nighttime
    0.86
     noon
    0.83
    noon
    0.82
     Moon
    0.81
    terday
    0.81
     nights
    0.79
    Activations Density 0.098%

    No Known Activations