© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 8-RES-JB
    11. 14127
    Prev
    Next
    INDEX
    Explanations

    phrases related to events or activities

    oai_token-act-pair · gpt-3.5-turbo

    terms related to various forms of celebration and activity

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
    Ire
    -0.82
    âĸ¬
    -0.81
    Recomm
    -0.73
    ×ŀ
    -0.72
    Honest
    -0.68
    Lear
    -0.68
    ãĤ©
    -0.68
    PLA
    -0.67
    Leaks
    -0.66
    Args
    -0.65
    POSITIVE LOGITS
     abound
    1.10
    mith
    1.09
     are
    0.95
    etting
    0.94
     aren
    0.92
    ystem
    0.91
    uits
    0.91
    hips
    0.89
    hip
    0.89
    pring
    0.89
    Activations Density 0.502%

    No Known Activations