© 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. 6-RES-JB
    11. 17135
    Prev
    Next
    INDEX
    Explanations

    phrases related to weight or comparison of weight

    oai_token-act-pair · gpt-3.5-turbo

    references to weight measurement and weighing in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    RIPT
    -0.78
    \\\\\\\\
    -0.75
    İĭ
    -0.73
    RECT
    -0.72
     Opportun
    -0.71
    arthed
    -0.71
     Wonderland
    -0.70
    ardy
    -0.70
    ĨĴ
    -0.69
     Shank
    -0.68
    POSITIVE LOGITS
     weighing
    1.01
     weighs
    1.00
     weigh
    0.95
     lbs
    0.89
     weights
    0.88
     weighed
    0.88
     suitcase
    0.83
    lbs
    0.81
     heaviest
    0.81
     pros
    0.79
    Activations Density 0.101%

    No Known Activations