© 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. 1-RES-JB
    11. 12785
    Prev
    Next
    INDEX
    Explanations

    political terms or concepts

    oai_token-act-pair · gpt-3.5-turbo

    mentions of political issues and concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    upon
    -0.75
     Om
    -0.71
    shall
    -0.71
     Landing
    -0.68
    tered
    -0.68
    ance
    -0.68
     Trinity
    -0.68
     Peaks
    -0.68
     Shannon
    -0.68
    anta
    -0.67
    POSITIVE LOGITS
     affili
    0.89
     correctness
    0.88
     disag
    0.84
     correct
    0.82
     politically
    0.80
     minded
    0.79
     aven
    0.77
     Pengu
    0.76
     oriented
    0.75
     savvy
    0.74
    Activations Density 0.005%

    No Known Activations