© 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. 12-RES-JB
    11. 4544
    Prev
    Next
    INDEX
    Explanations

    references to household items, specifically related to tableware and home furnishings

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot

    references to tables and surfaces

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 12-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.hook_resid_post
    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_post
    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
     Channel
    -0.66
     Directorate
    -0.66
     ounce
    -0.62
     Enhancement
    -0.61
     Banks
    -0.60
    rily
    -0.60
    vernment
    -0.59
    ovich
    -0.59
     Xer
    -0.58
     chancellor
    -0.58
    POSITIVE LOGITS
    cloth
    1.47
    au
    1.29
    aux
    1.28
    top
    1.14
    tops
    1.10
    poons
    0.99
    aus
    0.97
     tennis
    0.95
    poon
    0.90
     manners
    0.90
    Activations Density 0.054%

    No Known Activations