© 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. 6-RES-JB
    11. 17381
    Prev
    Next
    INDEX
    Explanations

    phrases related to specific organizations such as government agencies, research institutes, and health centers

    oai_token-act-pair · gpt-3.5-turbo

    conjunctions, particularly the word "and"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    helps
    -0.75
    wolf
    -0.74
    wings
    -0.73
    keyes
    -0.69
    rises
    -0.69
    rats
    -0.67
    nels
    -0.66
    lins
    -0.66
    depending
    -0.65
     toget
    -0.65
    POSITIVE LOGITS
     Accountability
    0.98
     Associates
    0.94
     Development
    0.92
     Technology
    0.90
     Evaluation
    0.88
     Cooperation
    0.87
     Engineering
    0.87
     Services
    0.86
     Telecommunications
    0.85
     Emergency
    0.84
    Activations Density 0.120%

    No Known Activations