© 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. 10-RES-JB
    11. 5503
    Prev
    Next
    INDEX
    Explanations

    ways or methods to address various challenges or problems

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating methods or processes for achieving specific outcomes or improvements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    comments
    -0.83
     Thoughts
    -0.82
     Lonely
    -0.80
     Concern
    -0.79
     Passion
    -0.77
     Discussion
    -0.76
     Worth
    -0.75
     Opinion
    -0.74
    endar
    -0.74
    ij士
    -0.74
    POSITIVE LOGITS
     simulate
    1.59
     manipulate
    1.43
     detect
    1.40
     efficiently
    1.33
     achieve
    1.33
     automate
    1.33
     reproduce
    1.32
     optimize
    1.30
     generate
    1.30
     extract
    1.29
    Activations Density 0.264%

    No Known Activations