© 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. 0-RES-JB
    11. 20132
    Prev
    Next
    INDEX
    Explanations

    references to the political party "Democrats"

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the Democratic Party

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     realise
    -0.65
    eon
    -0.62
     trainer
    -0.62
    Unit
    -0.61
     realised
    -0.61
     tuber
    -0.60
     cu
    -0.60
    kil
    -0.59
     ©
    -0.59
    âĸĪâĸĪâĸĪâĸĪ
    -0.59
    POSITIVE LOGITS
     Democrats
    3.61
    Democrats
    3.14
     Republicans
    2.80
     Dems
    2.67
     Democrat
    2.54
    Republicans
    2.49
     Democratic
    2.40
     democr
    2.26
    Democratic
    2.15
     liberals
    2.07
    Activations Density 0.017%

    No Known Activations