© 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. 11-RES-JB
    11. 9519
    Prev
    Next
    INDEX
    Explanations

    references to Pew Research and data analysis

    oai_token-act-pair · gpt-3.5-turbo

    references to the Pew Research Center and its surveys

    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
     Yanuk
    -0.69
    stood
    -0.68
     ultras
    -0.68
     suited
    -0.64
    mx
    -0.62
     Yanukovych
    -0.60
     optionally
    -0.60
     forgiven
    -0.59
     disorderly
    -0.59
     Horus
    -0.59
    POSITIVE LOGITS
    aukee
    1.21
     Research
    1.16
    Die
    0.99
    Research
    0.96
     Institution
    0.94
     Hispanic
    0.87
    study
    0.87
     Analytics
    0.86
     Forum
    0.85
     survey
    0.85
    Activations Density 0.037%

    No Known Activations