© 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. 14201
    Prev
    Next
    INDEX
    Explanations

    terms related to education and professional fields

    oai_token-act-pair · gpt-3.5-turbo

    terms and phrases related to various fields of health, care, and social sciences

    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
    luaj
    -0.69
    huge
    -0.68
    ĸļ
    -0.67
     Panzer
    -0.66
     endif
    -0.64
    urbed
    -0.62
    iless
    -0.61
     typo
    -0.61
    externalActionCode
    -0.61
     TAMADRA
    -0.61
    POSITIVE LOGITS
     services
    1.03
    services
    0.95
     systems
    0.89
     products
    0.86
    arers
    0.84
     programs
    0.84
     professionals
    0.83
    iaries
    0.83
     providers
    0.82
     environments
    0.82
    Activations Density 0.473%

    No Known Activations