© 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. 10-RES-JB
    11. 8567
    Prev
    Next
    INDEX
    Explanations

    words related to specific languages and cultures

    oai_token-act-pair · gpt-3.5-turbo

    linguistic or cultural connections between different ethnic groups

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     lasers
    -0.73
     plaintiff
    -0.70
     whistleblower
    -0.70
     McH
    -0.69
     watts
    -0.68
     whistleblowers
    -0.67
     Courage
    -0.66
     balloons
    -0.66
     malf
    -0.66
     Watson
    -0.65
    POSITIVE LOGITS
    onian
    1.41
    ussian
    1.28
    iterranean
    1.25
    nian
    1.20
    ocene
    1.18
    rican
    1.18
    inese
    1.17
    anian
    1.14
    adian
    1.13
    uvian
    1.13
    Activations Density 0.210%

    No Known Activations