© 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. 8-RES-JB
    11. 13122
    Prev
    Next
    INDEX
    Explanations

    ages and age-related information

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to age restrictions and demographic groups

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Negative Logits
     havoc
    -0.68
     Subtle
    -0.64
    ity
    -0.64
    Quotes
    -0.63
    atl
    -0.63
     Wast
    -0.62
    Voice
    -0.62
    risome
    -0.61
     Torrent
    -0.60
     goodbye
    -0.58
    POSITIVE LOGITS
    ileged
    0.95
     age
    0.93
     ages
    0.76
    insured
    0.76
     18
    0.75
    ¿
    0.74
     lvl
    0.73
     65
    0.72
    married
    0.72
     eighteen
    0.71
    Activations Density 0.165%

    No Known Activations