© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 11-RES-JB
    11. 13548
    Prev
    Next
    INDEX
    Explanations

    terms related to political ideologies and movements, particularly those associated with the alt-right

    oai_token-act-pair · gpt-3.5-turbo

    references to extreme political ideologies or movements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     deliveries
    -0.78
     Garr
    -0.77
     repay
    -0.72
     Tata
    -0.72
     parcels
    -0.71
     lease
    -0.70
     bidding
    -0.70
     Dart
    -0.69
     supervised
    -0.69
     delivery
    -0.69
    POSITIVE LOGITS
    acists
    1.40
    ivism
    1.32
     feminists
    1.32
    femin
    1.27
    acist
    1.26
     liberals
    1.25
    ophobic
    1.24
    conservative
    1.24
    liberal
    1.23
    ophob
    1.23
    Activations Density 0.368%

    No Known Activations