© 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. 4421
    Prev
    Next
    INDEX
    Explanations

    words associated with legal disputes and conflicts

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

    phrases indicating change or conflict in a narrative

    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
     awa
    -0.74
     ALWAYS
    -0.67
     ignor
    -0.67
     haha
    -0.67
     compuls
    -0.65
     liking
    -0.63
     sacrific
    -0.63
     NEVER
    -0.62
     contrace
    -0.62
     invincible
    -0.61
    POSITIVE LOGITS
    é¾įåĸļ士
    0.72
     amid
    0.70
    é¾įå
    0.68
    plom
    0.68
    YD
    0.68
     Republicans
    0.66
     Gov
    0.65
     GOP
    0.64
    Republicans
    0.64
     McConnell
    0.63
    Activations Density 0.473%

    No Known Activations