© 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. 7883
    Prev
    Next
    INDEX
    Explanations

    references to individuals' ages

    oai_token-act-pair · gpt-3.5-turbo

    numerical age values associated with people

    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
    berus
    -0.60
     Replay
    -0.54
     clos
    -0.54
    cru
    -0.51
    among
    -0.51
     lows
    -0.51
     incidental
    -0.51
    .):
    -0.50
     appro
    -0.49
    drawn
    -0.49
    POSITIVE LOGITS
     year
    1.28
    year
    1.15
    -
    1.04
     yr
    1.01
     Year
    0.93
    yr
    0.92
    Year
    0.90
     month
    0.85
    -[
    0.81
    something
    0.81
    Activations Density 0.077%

    No Known Activations