© 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. 2-RES-JB
    11. 6618
    Prev
    Next
    INDEX
    Explanations

    phrases related to political and social issues, specifically focusing on perspectives around marriage, abortion, gun ownership, and transgender rights

    oai_token-act-pair · gpt-3.5-turbo

    terms related to LGBTQ+ rights and marriage equality

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Univers
    -0.81
     Dh
    -0.77
    ãĤ¨ãĥ«
    -0.77
     Worm
    -0.77
     Outlook
    -0.75
     Dynam
    -0.73
    orp
    -0.73
     Hitchcock
    -0.73
     Ran
    -0.73
     LIA
    -0.73
    POSITIVE LOGITS
     legalization
    1.20
     laws
    1.10
     legalized
    1.09
     legalizing
    1.05
     statewide
    0.99
     repeal
    0.98
     unconstitutional
    0.97
     decriminal
    0.97
     disenfranch
    0.96
     ordinances
    0.95
    Activations Density 0.347%

    No Known Activations