© 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. 9-RES-JB
    11. 18225
    Prev
    Next
    INDEX
    Explanations

    terms related to political and geopolitical topics

    oai_token-act-pair · gpt-3.5-turbo

    terms related to various forms of political, ethical, and geopolitical 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
    bsite
    -0.77
    pherd
    -0.72
    ħĭ
    -0.72
    essee
    -0.71
    ipop
    -0.71
    plin
    -0.71
    igun
    -0.70
    essor
    -0.70
    ulhu
    -0.70
    cius
    -0.69
    POSITIVE LOGITS
     ramifications
    1.22
     significance
    1.18
     advantages
    1.18
     considerations
    1.17
     implications
    1.17
     repercussions
    1.15
     consequences
    1.14
     sophistication
    1.07
     importance
    1.05
     reasons
    1.05
    Activations Density 0.265%

    No Known Activations