© 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. 2307
    Prev
    Next
    INDEX
    Explanations

    phrases related to political majorities or votes

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of majority in decision-making processes

    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
    glers
    -0.78
    bons
    -0.74
    uras
    -0.72
    videos
    -0.70
     Gutenberg
    -0.68
    nels
    -0.68
    lov
    -0.66
    oras
    -0.65
    skirts
    -0.65
    paralle
    -0.65
    POSITIVE LOGITS
     opinion
    1.09
     shareholder
    0.88
     vote
    0.85
     stake
    0.80
    majority
    0.76
     majority
    0.73
     of
    0.73
    ipop
    0.72
     leader
    0.72
     share
    0.71
    Activations Density 0.036%

    No Known Activations