© 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. 2313
    Prev
    Next
    INDEX
    Explanations

    phrases related to politics and historical events

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

    references to historical context and significant events

    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
     backer
    -0.71
     solicit
    -0.70
     solic
    -0.70
     pledging
    -0.68
     partner
    -0.68
     donor
    -0.65
     PW
    -0.65
     fundraiser
    -0.64
     offering
    -0.64
     indemn
    -0.63
    POSITIVE LOGITS
    history
    1.31
    ISTORY
    1.26
     historians
    1.25
     eras
    1.14
    Ancient
    1.11
    ieval
    1.10
    eteenth
    1.06
     century
    1.05
     1927
    1.05
     1910
    1.05
    Activations Density 0.805%

    No Known Activations