© 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 EvalsExportsinterp-engineNEWAPI 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. 21122
    Prev
    Next
    INDEX
    Explanations

    large numerical values

    oai_token-act-pair · gpt-3.5-turbo

    references to large numerical values or statistics, particularly in the millions

    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
     queues
    -0.86
     histories
    -0.81
    ties
    -0.78
     angles
    -0.78
    casts
    -0.74
     forks
    -0.73
     lows
    -0.72
     highs
    -0.72
     ages
    -0.71
     fences
    -0.71
    POSITIVE LOGITS
    st
    1.28
    Password
    1.23
    125
    1.08
    120
    0.96
    ½
    0.96
    âģ
    0.85
    123
    0.84
    128
    0.84
    RM
    0.83
     kilomet
    0.82
    Activations Density 0.070%

    No Known Activations