© 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. 2290
    Prev
    Next
    INDEX
    Explanations

    descriptions of upcoming events and activities

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

    phrases indicating time or future actions

    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
    furt
    -0.82
    FactoryReloaded
    -0.81
    intensive
    -0.78
    Lago
    -0.74
    ONSORED
    -0.74
    anooga
    -0.73
    hammad
    -0.73
    cyclopedia
    -0.72
    ė
    -0.71
    ğ
    -0.71
    POSITIVE LOGITS
     rejoice
    1.28
     bask
    1.25
     celebrate
    1.12
     indulge
    1.07
     snag
    1.02
     revel
    1.01
     unleash
    1.00
     feast
    1.00
     commemorate
    0.98
     revisit
    0.96
    Activations Density 0.383%

    No Known Activations