© 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. 11-RES-JB
    11. 9458
    Prev
    Next
    INDEX
    Explanations

    age indicators in the format "number-number"

    oai_token-act-pair · gpt-3.5-turbo

    references to age and time periods related to young children

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Canaver
    -0.83
    icist
    -0.67
     SOFTWARE
    -0.62
     STATS
    -0.62
     Sole
    -0.58
     Invention
    -0.58
     Spotlight
    -0.57
    zsche
    -0.55
     Restaur
    -0.55
     Majority
    -0.55
    POSITIVE LOGITS
     olds
    1.30
    old
    1.10
    olds
    1.09
     old
    1.05
    Old
    0.95
    aged
    0.83
    worm
    0.83
    daughter
    0.83
     pregnant
    0.82
    girl
    0.79
    Activations Density 0.046%

    No Known Activations