© 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. 4-RES-JB
    11. 7446
    Prev
    Next
    INDEX
    Explanations

    phrases related to major issues or emergencies

    oai_token-act-pair · gpt-3.5-turbo

    references to crisis situations

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

    No Comments

    Negative Logits
    alty
    -0.89
    alties
    -0.89
    Īè
    -0.84
    olulu
    -0.82
    collar
    -0.81
    essee
    -0.81
    rosse
    -0.80
    ateur
    -0.80
    Ģ
    -0.80
    ¿½
    -0.79
    POSITIVE LOGITS
     crisis
    1.02
     Crisis
    0.90
     engulf
    0.87
     plag
    0.84
     outbreak
    0.84
     crises
    0.83
     aver
    0.82
     epidemic
    0.82
     erupt
    0.79
     escalated
    0.78
    Activations Density 0.020%

    No Known Activations