© 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. 8-RES-JB
    11. 6331
    Prev
    Next
    INDEX
    Explanations

    terms related to societal issues, such as poverty, violence, discrimination, and regulations

    oai_token-act-pair · gpt-3.5-turbo

    issues related to systemic inequality and social justice

    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
    ¬¼
    -0.70
    itone
    -0.69
    ģĸ
    -0.64
    ãĤ¦ãĤ¹
    -0.64
    quet
    -0.63
    atically
    -0.63
    itus
    -0.61
    lor
    -0.60
    identally
    -0.59
    ady
    -0.59
    POSITIVE LOGITS
     etc
    0.95
     namely
    0.76
    sed
    0.76
     including
    0.75
     albeit
    0.75
    Magikarp
    0.69
     but
    0.67
     whereas
    0.66
     which
    0.64
    advertising
    0.63
    Activations Density 0.273%

    No Known Activations