© 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. 3-RES-JB
    11. 16635
    Prev
    Next
    INDEX
    Explanations

    terms related to multiculturalism

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of "multi" or "multicultural."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    OPLE
    -0.88
    HOME
    -0.84
    çĶ°
    -0.81
     Tigers
    -0.75
     Wolves
    -0.75
     Defenders
    -0.75
     Warriors
    -0.74
    à©
    -0.74
    姫
    -0.73
    Ö¼
    -0.71
    POSITIVE LOGITS
    icol
    1.24
    ilingual
    1.20
    ivariate
    1.15
    itud
    1.13
    iversal
    1.10
    ivari
    1.05
    iques
    1.03
    ipl
    1.03
    ilateral
    1.01
    ilater
    0.98
    Activations Density 0.007%

    No Known Activations