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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 12247
    Prev
    Next
    INDEX
    Explanations

    controversial or sensational news headlines containing specific terms such as racial references, medical terms or political figures

    oai_token-act-pair · gpt-3.5-turbo

    terms related to sports, particularly basketball

    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
     tremend
    -1.03
     aven
    -0.95
     bonded
    -0.93
     estab
    -0.92
     referen
    -0.91
     complementary
    -0.89
     accumulated
    -0.89
     senate
    -0.88
     crest
    -0.87
     snowball
    -0.87
    POSITIVE LOGITS
     Coverage
    1.43
     Prices
    1.41
     Programs
    1.40
     Costs
    1.40
     Issues
    1.38
     Problems
    1.37
     Practices
    1.37
     Plans
    1.36
     Policies
    1.36
     Claims
    1.35
    Activations Density 0.394%

    No Known Activations