© 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 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. 9-RES-JB
    11. 1127
    Prev
    Next
    INDEX
    Explanations

    scientific and technical terms, particularly related to materials and experiments

    oai_token-act-pair · gpt-3.5-turbo

    technical terms and measurements related to scientific research

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    iquette
    -0.89
     etiquette
    -0.85
     admins
    -0.76
     lobb
    -0.74
     professions
    -0.71
     parenting
    -0.71
     ACLU
    -0.68
     privacy
    -0.68
     reps
    -0.67
     patrons
    -0.67
    POSITIVE LOGITS
     isot
    1.07
     cubic
    0.96
     uranium
    0.95
     radioactive
    0.93
     ammon
    0.92
    utonium
    0.92
    hyd
    0.89
     hydro
    0.89
    idium
    0.88
     neutron
    0.87
    Activations Density 0.760%

    No Known Activations