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

    Neuronpedia

    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. 11-RES-JB
    11. 6523
    Prev
    Next
    INDEX
    Explanations

    terms related to controversial social and political issues

    oai_token-act-pair · gpt-3.5-turbo

    references to significant social and political issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ngth
    -0.82
    esters
    -0.82
    blers
    -0.78
     Pwr
    -0.69
    externalActionCode
    -0.69
    ridor
    -0.69
    wait
    -0.67
    Timer
    -0.67
    appointed
    -0.66
    upt
    -0.66
    POSITIVE LOGITS
     topics
    2.11
     issues
    1.74
     subjects
    1.71
     matters
    1.66
     controversies
    1.48
     topic
    1.47
    issues
    1.43
     themes
    1.33
     topical
    1.33
     Topics
    1.32
    Activations Density 0.523%

    No Known Activations