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

    Neuronpedia

    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. 9-RES-JB
    11. 13639
    Prev
    Next
    INDEX
    Explanations

    time-related phrases, especially referring to specific periods or seasons

    oai_token-act-pair · gpt-3.5-turbo

    references to time periods and seasons

    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
     Cosponsors
    -0.77
     locations
    -0.68
     nods
    -0.65
     spots
    -0.63
     strengths
    -0.63
     views
    -0.62
    hots
    -0.62
     rooft
    -0.60
     weaknesses
    -0.60
    facts
    -0.59
    POSITIVE LOGITS
     season
    1.15
     millennium
    0.99
     cycle
    0.99
    imester
    0.94
     semester
    0.94
     era
    0.90
     century
    0.89
     month
    0.89
    season
    0.85
    enium
    0.83
    Activations Density 0.213%

    No Known Activations