© 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. 13909
    Prev
    Next
    INDEX
    Explanations

    mentions of political and governmental issues or reforms

    oai_token-act-pair · gpt-3.5-turbo

    topics related to social and educational reforms

    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
     rumors
    -1.07
    colored
    -1.03
     colorful
    -1.03
     demeanor
    -1.00
     humor
    -0.94
     apologize
    -0.94
     rumor
    -0.91
     traveled
    -0.90
     maneuvers
    -0.89
     honored
    -0.89
    POSITIVE LOGITS
     NHS
    1.76
     £
    1.75
    £
    1.55
     programmes
    1.49
    Scotland
    1.42
     programme
    1.37
     Labour
    1.33
    Labour
    1.32
     organisations
    1.31
     Scotland
    1.31
    Activations Density 0.964%

    No Known Activations