© 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. 10528
    Prev
    Next
    INDEX
    Explanations

    phrases related to diverse opinions, freedom of expression, and open discourse

    oai_token-act-pair · gpt-3.5-turbo

    discussions about political opinions and the right to express them

    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
    ©¶æ¥µ
    -0.75
    mallow
    -0.75
     Storage
    -0.72
     Nurs
    -0.71
     Married
    -0.71
     wastewater
    -0.70
     Rehab
    -0.70
     kidnapping
    -0.70
     Magicka
    -0.70
    aceae
    -0.69
    POSITIVE LOGITS
     viewpoints
    1.67
     opinions
    1.67
     opin
    1.43
     opinion
    1.40
     truths
    1.34
     dissenting
    1.33
     disagree
    1.33
     views
    1.30
     disagrees
    1.30
     conclusions
    1.29
    Activations Density 0.659%

    No Known Activations