© 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. 14132
    Prev
    Next
    INDEX
    Explanations

    words ending in 'ing' that are part of URLs

    oai_token-act-pair · gpt-3.5-turbo

    titles of successful films along with their box office earnings

    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
     steroids
    -0.36
    enegger
    -0.35
     stocking
    -0.35
     pods
    -0.35
     behav
    -0.34
    sic
    -0.34
     grounding
    -0.34
     stacks
    -0.34
     curric
    -0.34
     respons
    -0.33
    POSITIVE LOGITS
    ®
    0.54
    º
    0.48
    £
    0.45
    ¢
    0.45
    ¯
    0.45
    IJ
    0.45
    ī
    0.45
    Ģ
    0.44
     ):
    0.43
    §
    0.43
    Activations Density 1.413%

    No Known Activations