© 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. 3450
    Prev
    Next
    INDEX
    Explanations

    descriptions related to personal appearance and lifestyle

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

    expressions and phrases related to abundance or excess

    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
    Ĥ¬
    -0.69
    ciation
    -0.66
    ells
    -0.66
    saf
    -0.64
    Stand
    -0.64
    osate
    -0.63
    devices
    -0.62
    Cs
    -0.61
    rices
    -0.61
    ²¾
    -0.60
    POSITIVE LOGITS
     time
    1.20
     nights
    1.15
     weekends
    1.14
     evenings
    1.11
     slee
    1.07
     hours
    1.03
     waking
    1.02
     summers
    1.01
     Saturdays
    0.97
     Sundays
    0.97
    Activations Density 0.074%

    No Known Activations