© 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. 12-RES-JB
    11. 4026
    Prev
    Next
    INDEX
    Explanations

    words related to politics and controversies, especially surrounding emails and scandals

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot

    references to email usage and discussions surrounding trans identity and rights

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 12-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.hook_resid_post
    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_post
    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
    SHIP
    -0.63
    igne
    -0.62
    odcast
    -0.61
    mort
    -0.60
    ILLE
    -0.59
    lost
    -0.57
     consequ
    -0.57
    crow
    -0.56
    onal
    -0.55
    directed
    -0.54
    POSITIVE LOGITS
    çİĭ
    0.58
     dictator
    0.57
     patriotism
    0.55
     patriot
    0.54
     billionaire
    0.54
    ="
    0.53
    çĶŁ
    0.53
     resemble
    0.52
    ãģ®éŃĶ
    0.51
     Liberty
    0.51
    Activations Density 0.485%

    No Known Activations