© 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. 7574
    Prev
    Next
    INDEX
    Explanations

    political figures and government institutions

    oai_token-act-pair · gpt-3.5-turbo

    references to political entities and individuals in various contexts

    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
     disappeared
    -0.83
     vanished
    -0.74
     died
    -0.71
     replaced
    -0.70
    Joined
    -0.62
     };
    -0.62
     PLUS
    -0.62
     crashed
    -0.62
     disappears
    -0.61
     inactive
    -0.60
    POSITIVE LOGITS
    erning
    0.96
     policymakers
    0.84
    antics
    0.79
     thinking
    0.76
     wondering
    0.76
     contemplating
    0.75
     puzzling
    0.74
     understandably
    0.74
     hesitate
    0.72
     puzz
    0.70
    Activations Density 0.505%

    No Known Activations