© 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. 15454
    Prev
    Next
    INDEX
    Explanations

    phrases related to political ideologies, specifically focusing on differences between conservatives and liberals

    oai_token-act-pair · gpt-3.5-turbo

    references to political affiliations, particularly conservatives and liberals

    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
    Delivery
    -0.83
    Owner
    -0.69
     Bulldogs
    -0.68
    BY
    -0.67
     circumstances
    -0.63
    inventoryQuantity
    -0.63
     submission
    -0.62
     Territories
    -0.61
     increments
    -0.61
     completion
    -0.59
    POSITIVE LOGITS
    ervatives
    1.39
    ervative
    1.36
    paces
    1.19
    aurus
    1.05
     rejoice
    0.97
    pace
    0.92
    '
    0.87
    mith
    0.85
    hift
    0.85
    chool
    0.82
    Activations Density 0.081%

    No Known Activations