© 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. 10-RES-JB
    11. 20674
    Prev
    Next
    INDEX
    Explanations

    titles or terms related to action, combat, and conflict

    oai_token-act-pair · gpt-3.5-turbo

    terms related to action and combat in entertainment media

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    liness
    -0.81
     toget
    -0.69
    matically
    -0.67
    hips
    -0.65
    yssey
    -0.65
    ily
    -0.65
    iannopoulos
    -0.65
     proceeding
    -0.64
     challeng
    -0.63
    itiz
    -0.63
    POSITIVE LOGITS
     Zone
    1.12
     Squad
    1.11
     Desk
    1.11
     Corps
    1.08
     Disorders
    1.05
     Committee
    1.05
     Room
    1.03
     Grounds
    1.02
     Club
    1.02
     Mode
    1.01
    Activations Density 0.193%

    No Known Activations