© 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. 12-RES-JB
    11. 2316
    Prev
    Next
    INDEX
    Explanations

    descriptions of different types of hairstyles for men

    oai_token-act-pair · gpt-3.5-turbo
    Triggered by @bot

    various hairstyles for men, particularly highlighting popular styles and techniques

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 12-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.hook_resid_post
    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_post
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
    SQL
    -0.80
    greSQL
    -0.78
     Romero
    -0.77
    Player
    -0.76
    sql
    -0.75
    Äį
    -0.75
     Gutenberg
    -0.73
    Disk
    -0.73
     SERV
    -0.73
     sidx
    -0.73
    POSITIVE LOGITS
     hair
    1.93
     hairst
    1.79
     hairs
    1.79
     curls
    1.76
     Hair
    1.69
     scalp
    1.68
     shampoo
    1.65
     hairc
    1.65
     curly
    1.54
    hair
    1.50
    Activations Density 0.284%

    No Known Activations