© 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. 10-RES-JB
    11. 5548
    Prev
    Next
    INDEX
    Explanations

    phrases related to social issues or controversies

    oai_token-act-pair · gpt-3.5-turbo

    concepts related to social issues and critiques of societal narratives

    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
    actionDate
    -0.89
    Benz
    -0.76
    ij士
    -0.71
    »Ĵ
    -0.70
    ľ
    -0.70
    å¸
    -0.70
    VERT
    -0.70
    ģĸ
    -0.69
    IJ
    -0.68
    vernight
    -0.67
    POSITIVE LOGITS
     phenomenon
    1.49
     fallacy
    1.48
     hypothesis
    1.44
     analogy
    1.38
     loophole
    1.38
     theorem
    1.32
     trope
    1.31
     paradigm
    1.29
     concept
    1.28
     moniker
    1.27
    Activations Density 0.703%

    No Known Activations