© 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. 3-RES-JB
    11. 55
    Prev
    Next
    INDEX
    Explanations

    terms related to physical weight

    oai_token-act-pair · gpt-3.5-turbo

    references to weight, specifically emphasizing the concept in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    BLE
    -0.85
     Mb
    -0.84
    ICLE
    -0.80
     VIS
    -0.77
     Noir
    -0.75
     Suc
    -0.75
     Gutenberg
    -0.74
     Morse
    -0.71
    UTE
    -0.68
     Brist
    -0.68
    POSITIVE LOGITS
     weights
    1.10
     weight
    1.05
    weight
    1.01
    lifting
    1.00
    Weight
    0.96
    weights
    0.96
     heavier
    0.90
     burdens
    0.89
     heaviest
    0.87
    nutrition
    0.86
    Activations Density 0.014%

    No Known Activations