© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 8-RES-JB
    11. 8303
    Prev
    Next
    INDEX
    Explanations

    phrases and terms related to weight and weight loss

    oai_token-act-pair · gpt-3.5-turbo

    terms related to weight and weight loss

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ICLE
    -0.78
    BLE
    -0.75
    oral
    -0.72
    xon
    -0.70
     Mb
    -0.69
     Noir
    -0.68
     Gutenberg
    -0.67
     Suc
    -0.67
    etheless
    -0.66
    RPG
    -0.66
    POSITIVE LOGITS
    lifting
    1.24
    lif
    1.01
    weight
    0.98
    weights
    0.94
    lessness
    0.94
     lifting
    0.92
     weights
    0.90
     weight
    0.86
     heaviest
    0.85
    loss
    0.85
    Activations Density 0.034%

    No Known Activations