© 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. 7-RES-JB
    11. 14303
    Prev
    Next
    INDEX
    Explanations

    words related to Political Action Committees (PACs)

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    lihood
    -0.80
    hower
    -0.72
    pots
    -0.67
    ãĤª
    -0.66
     Qi
    -0.65
     quot
    -0.64
    demand
    -0.63
     Yi
    -0.62
    ãĥĥãĥī
    -0.62
     Thames
    -0.62
    POSITIVE LOGITS
    IFIC
    1.28
    eers
    1.00
     treasurer
    0.85
    rolled
    0.80
     coffers
    0.80
    oola
    0.79
    ERN
    0.78
    ocobo
    0.76
     operative
    0.76
    BLIC
    0.75
    Activations Density 0.039%

    No Known Activations