© 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. 3-RES-JB
    11. 9075
    Prev
    Next
    INDEX
    Explanations

    technical and procedural details or instructions

    oai_token-act-pair · gpt-3.5-turbo

    connections and relationships between components or concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    SPONSORED
    -0.91
    Islam
    -0.80
    AIDS
    -0.78
    gay
    -0.74
    deen
    -0.72
    Islamic
    -0.70
    Muslim
    -0.70
     AIDS
    -0.69
     ÂŃ
    -0.69
    Jews
    -0.67
    POSITIVE LOGITS
     setup
    0.92
     functionality
    0.90
     usability
    0.87
     optimized
    0.86
     workflow
    0.85
     optimization
    0.85
     modular
    0.84
     customization
    0.82
     backend
    0.82
     plugin
    0.81
    Activations Density 2.469%

    No Known Activations