© 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. 11334
    Prev
    Next
    INDEX
    Explanations

    mentions of laws related to criminalizing or regulating homosexuality

    oai_token-act-pair · gpt-3.5-turbo

    references to legal restrictions on homosexuality and human rights issues

    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
    apeake
    -0.84
     Dealer
    -0.84
     Podesta
    -0.83
     Avg
    -0.82
     DOE
    -0.81
     Omaha
    -0.81
     Ops
    -0.80
    NAS
    -0.80
     Velocity
    -0.79
     Amtrak
    -0.78
    POSITIVE LOGITS
     blasphemy
    1.58
     Sharia
    1.46
     outlawed
    1.45
     compulsory
    1.41
     punishable
    1.41
     banned
    1.40
     banning
    1.38
     homosexuality
    1.36
     bans
    1.34
     decriminal
    1.31
    Activations Density 1.018%

    No Known Activations