© 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. 6-RES-JB
    11. 11873
    Prev
    Next
    INDEX
    Explanations

    words related to political and social systems, specifically focusing on terms related to mediocrity and democracy

    oai_token-act-pair · gpt-3.5-turbo

    terms related to various forms of government and political themes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ting
    -0.86
    ster
    -0.78
    ing
    -0.75
    listed
    -0.71
    ez
    -0.70
    staking
    -0.67
    ful
    -0.65
    bang
    -0.63
    fully
    -0.62
    ning
    -0.62
    POSITIVE LOGITS
    acies
    0.97
    atism
    0.90
    kefeller
    0.87
    atically
    0.84
    ocracy
    0.83
    ocratic
    0.79
    phia
    0.77
    ocr
    0.76
    atics
    0.76
    asms
    0.75
    Activations Density 0.084%

    No Known Activations