© 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. 10-RES-JB
    11. 23487
    Prev
    Next
    INDEX
    Explanations

    dates in the format "Month Year" when looking at the document

    oai_token-act-pair · gpt-3.5-turbo

    occurrences and references to specific dates and moments in time

    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
     356
    -0.88
     Hawai
    -0.85
     Io
    -0.84
     351
    -0.83
     Giov
    -0.80
     Pilgrim
    -0.79
    opl
    -0.78
    ili
    -0.77
     Laur
    -0.77
     Rag
    -0.76
    POSITIVE LOGITS
    ter
    1.19
    TER
    1.11
    ters
    1.02
     December
    1.01
    cember
    0.98
    tering
    0.97
    dec
    0.96
    tered
    0.93
    ester
    0.90
    down
    0.90
    Activations Density 0.305%

    No Known Activations