© 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. 9-RES-JB
    11. 16609
    Prev
    Next
    INDEX
    Explanations

    mentions of legal cases and political events involving discrimination or controversial issues

    oai_token-act-pair · gpt-3.5-turbo

    significant legal and political events related to LGBTQ+ issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     tomorrow
    -0.77
     tonight
    -0.72
    morrow
    -0.66
    ********************************
    -0.65
     today
    -0.63
    whatever
    -0.62
    asionally
    -0.61
    Thursday
    -0.60
    )))
    -0.60
     lately
    -0.60
    POSITIVE LOGITS
     unsuccessfully
    0.84
     resulted
    0.79
     famously
    0.71
     blamed
    0.69
    oided
    0.66
     controvers
    0.65
     mistakenly
    0.63
     disrupted
    0.62
    ¿½
    0.61
    ixty
    0.60
    Activations Density 1.271%

    No Known Activations