© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 2-RES-JB
    11. 504
    Prev
    Next
    INDEX
    Explanations

    words related to authoritarian measures, specifically the term "crackdown"

    oai_token-act-pair · gpt-4-turbo

    instances of the word "crackdown."

    oai_token-act-pair · gpt-3.5-turbo

    terms related to governmental or law enforcement actions against dissent or civil liberties

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    tein
    -0.82
     Lakes
    -0.75
    esthetic
    -0.72
     Dominion
    -0.69
    ces
    -0.69
    hof
    -0.69
    izable
    -0.67
    ports
    -0.64
    Dan
    -0.64
    par
    -0.63
    POSITIVE LOGITS
     crackdown
    1.34
     clamp
    0.91
     undermin
    0.79
     enforcement
    0.74
     repression
    0.73
     Rohing
    0.72
     shenan
    0.71
     roundup
    0.71
     conflic
    0.70
    ollah
    0.70
    Activations Density 0.014%

    No Known Activations