© 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. 9-RES-JB
    11. 15531
    Prev
    Next
    INDEX
    Explanations

    mentions of political opposition or opposing parties

    oai_token-act-pair · gpt-3.5-turbo

    mentions of political opposition

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    med
    -0.80
    mson
    -0.76
    cise
    -0.76
    ãĤ¨ãĥ«
    -0.75
    thur
    -0.73
    ulative
    -0.71
    ifter
    -0.71
    ls
    -0.71
    asu
    -0.70
    bilt
    -0.69
    POSITIVE LOGITS
     parties
    0.98
     coalition
    0.83
     bloc
    0.81
     groups
    0.80
     factions
    0.79
     viewpoints
    0.78
     Aven
    0.77
     party
    0.75
     stronghold
    0.75
     leader
    0.75
    Activations Density 0.046%

    No Known Activations