© 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. 11-RES-JB
    11. 11399
    Prev
    Next
    INDEX
    Explanations

    expressions related to weight management and physical weight changes

    oai_token-act-pair · gpt-3.5-turbo

    references related to weight and weight-related issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    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
    etheless
    -0.85
    BLE
    -0.74
    uber
    -0.72
    opsis
    -0.69
    vironment
    -0.69
    ovie
    -0.68
     VIS
    -0.67
    herry
    -0.66
     Noir
    -0.66
     Myster
    -0.64
    POSITIVE LOGITS
    lifting
    1.44
    lif
    1.10
    loss
    0.97
    lessness
    0.96
     gain
    0.95
     lifting
    0.94
     loss
    0.90
     regain
    0.83
    bearing
    0.82
    cake
    0.82
    Activations Density 0.049%

    No Known Activations