© 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 EvalsExportsinterp-engineNEWAPI 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. 3256
    Prev
    Next
    INDEX
    Explanations

    phrases related to cultural and political opinions

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot

    references to controversial societal and political discussions

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

    No Comments

    Negative Logits
    ngth
    -0.94
    oso
    -0.79
    ridor
    -0.77
    esters
    -0.75
     Pwr
    -0.72
    vation
    -0.70
    externalActionCode
    -0.70
    enos
    -0.69
    upt
    -0.68
    appointed
    -0.67
    POSITIVE LOGITS
     topics
    1.79
     subjects
    1.51
     issues
    1.47
     matters
    1.40
     topical
    1.34
     controversies
    1.33
    issues
    1.23
     contentious
    1.21
     controversial
    1.20
     topic
    1.20
    Activations Density 0.497%

    No Known Activations