© 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. 7810
    Prev
    Next
    INDEX
    Explanations

    references to the "Tea Party" political movement

    oai_token-act-pair · gpt-3.5-turbo

    references to the Tea Party movement

    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
    theless
    -0.95
    osure
    -0.80
    ities
    -0.77
    istically
    -0.75
    edly
    -0.71
    ion
    -0.67
    bage
    -0.67
    ospace
    -0.67
    oller
    -0.66
    phis
    -0.66
    POSITIVE LOGITS
     towels
    0.91
     Leaf
    0.89
    pees
    0.88
     kettle
    0.87
    pee
    0.86
    wife
    0.85
     Leaves
    0.84
     leaf
    0.80
     towel
    0.80
     gardens
    0.80
    Activations Density 0.037%

    No Known Activations