© 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. 2-RES-JB
    11. 13853
    Prev
    Next
    INDEX
    Explanations

    political figures, political actions, and governmental terms

    oai_token-act-pair · gpt-3.5-turbo

    references to government and political processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Leilan
    -0.51
    OVA
    -0.51
    é¾įå
    -0.51
    æµ
    -0.47
    ãĤ¨ãĥ«
    -0.46
     Moroc
    -0.46
    åħī
    -0.45
    Notable
    -0.45
    代
    -0.45
    pheus
    -0.45
    POSITIVE LOGITS
    sych
    0.52
    agy
    0.51
     DRAGON
    0.50
    atform
    0.50
    taboola
    0.48
     Marijuana
    0.48
     COURT
    0.47
    offic
    0.47
    reb
    0.46
    ndum
    0.46
    Activations Density 2.547%

    No Known Activations