© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 1-RES-JB
    11. 3226
    Prev
    Next
    INDEX
    Explanations

    words related to various types of crises

    oai_token-act-pair · gpt-3.5-turbo

    references to various types of crises

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ¿½
    -0.81
    alties
    -0.78
    essee
    -0.77
    ////////////////
    -0.76
    rica
    -0.76
    ingers
    -0.75
    ittle
    -0.75
    nda
    -0.74
    Īè
    -0.74
    Ĥ¬
    -0.73
    POSITIVE LOGITS
     crisis
    1.20
     Crisis
    1.03
     crises
    0.91
     epidemic
    0.86
     engulf
    0.86
     meltdown
    0.83
     Situation
    0.80
    risis
    0.78
     outbreak
    0.76
     eruption
    0.74
    Activations Density 0.016%

    No Known Activations