© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 11-RES-JB
    6. 7573
    Prev
    Next
    INDEX
    Explanations

    phrases related to diplomatic relations and agreements

    oai_token-act-pair · gpt-3.5-turbo

    expressions related to political agreements and diplomatic interactions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    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
    ueless
    -0.80
     abuser
    -0.79
    die
    -0.78
     dod
    -0.76
    quit
    -0.75
     screaming
    -0.75
    Lost
    -0.74
    Buzz
    -0.74
     TMZ
    -0.74
    paio
    -0.73
    POSITIVE LOGITS
     Cooperation
    1.32
     envis
    1.26
     strengthening
    1.25
     bilateral
    1.23
     cooperation
    1.22
     modernization
    1.12
     deepen
    1.07
     conducive
    1.07
     coordination
    1.04
     Armenia
    1.04
    Activations Density 0.660%

    No Known Activations