© 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. 14174
    Prev
    Next
    INDEX
    Explanations

    descriptions of individuals by age, gender, and clothing

    oai_token-act-pair · gpt-3.5-turbo

    references to young individuals, specifically teenagers and young adults

    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
    inventoryQuantity
    -0.76
     Cosponsors
    -0.75
    otation
    -0.75
    Versions
    -0.71
    yss
    -0.71
    ħĭ
    -0.69
    éĹĺ
    -0.68
    elines
    -0.67
    eeper
    -0.67
    abella
    -0.66
    POSITIVE LOGITS
     surrounded
    1.21
     sandwic
    1.08
     whose
    1.00
     striving
    1.00
     devoid
    0.96
     flanked
    0.95
     riddled
    0.95
     circa
    0.90
     tucked
    0.89
     crammed
    0.87
    Activations Density 0.547%

    No Known Activations