© 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. 8-RES-JB
    11. 3237
    Prev
    Next
    INDEX
    Explanations

    mentions of the politician Ron Paul

    oai_token-act-pair · gpt-3.5-turbo

    mentions of Ron Paul and his political activities or influence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    cyl
    -0.69
    Operation
    -0.67
     Yao
    -0.66
     Pixie
    -0.65
    Production
    -0.63
     Ning
    -0.60
     psychiat
    -0.60
     LIA
    -0.60
     lodge
    -0.60
     CLSID
    -0.59
    POSITIVE LOGITS
    sburg
    0.96
     supporters
    0.91
    roud
    0.90
    son
    0.86
    sonian
    0.82
    sen
    0.81
    ervative
    0.81
    ismo
    0.78
     supporter
    0.77
    istan
    0.77
    Activations Density 0.016%

    No Known Activations