© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 9-RES-JB
    11. 24323
    Prev
    Next
    INDEX
    Explanations

    references to cultural or religious symbols and practices

    oai_token-act-pair · gpt-3.5-turbo

    references to social or cultural symbols

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
     timelines
    -0.92
    izons
    -0.81
    doms
    -0.80
     Regions
    -0.80
     scenarios
    -0.78
    rosso
    -0.78
     counties
    -0.77
     Events
    -0.74
     Networks
    -0.74
     streams
    -0.72
    POSITIVE LOGITS
     worn
    1.35
     adorned
    1.17
     engraved
    1.15
     handmade
    1.11
     necklace
    1.11
     protr
    1.07
     wielded
    1.06
     decorative
    1.05
     souven
    1.05
     symbol
    1.04
    Activations Density 0.850%

    No Known Activations