© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 8-RES-JB
    6. 17804
    Prev
    Next
    INDEX
    Explanations

    words related to social or political issues, such as gun control, abortion rights, and more

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to gun control and associated issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Elm
    -0.65
     Starfleet
    -0.64
     Thick
    -0.64
     Rounds
    -0.62
     Moody
    -0.62
     leaps
    -0.60
     Despair
    -0.60
     sums
    -0.60
     square
    -0.60
     Jed
    -0.60
    POSITIVE LOGITS
    related
    1.74
    specific
    1.63
    centric
    1.56
    themed
    1.44
    centered
    1.43
    focused
    1.41
    associated
    1.36
    induced
    1.36
    friendly
    1.35
    loving
    1.29
    Activations Density 0.147%

    No Known Activations