© 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. 12849
    Prev
    Next
    INDEX
    Explanations

    terms related to legal and political actions, such as deportation, policy-making, and negotiations

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to immigration and state policies

    oai_token-act-pair · gpt-4o-miniTriggered 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
    Not in Any Lists

    No Comments

    Negative Logits
    asma
    -0.60
     Sung
    -0.57
     Bought
    -0.56
    reek
    -0.56
    \'
    -0.54
     Mystery
    -0.54
    ipeg
    -0.54
     Cros
    -0.53
    iple
    -0.53
    olo
    -0.52
    POSITIVE LOGITS
     thereby
    1.07
     preferably
    0.93
     lest
    0.83
     ensuring
    0.77
     maximizing
    0.74
     culminating
    0.73
     minimizing
    0.71
     leveraging
    0.70
     THEN
    0.68
     maximize
    0.68
    Activations Density 0.796%

    No Known Activations