Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 20249
    Prev
    Next
    INDEX
    Explanations

    nutrients essential for hair growth and health

    oai_token-act-pair · gpt-3.5-turbo

    references to vitamins and minerals in foods

    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
     Kafka
    -0.91
     Robots
    -0.90
    raints
    -0.90
    ttle
    -0.85
     Robotics
    -0.82
     Sting
    -0.80
     swarm
    -0.75
    cock
    -0.75
     Goff
    -0.75
     Drone
    -0.74
    POSITIVE LOGITS
     vitamin
    1.80
     Vitamin
    1.73
     vitamins
    1.66
     supplementation
    1.60
     antioxidants
    1.59
     antioxidant
    1.57
    itamin
    1.52
     calcium
    1.49
     magnesium
    1.48
     dietary
    1.45
    Activations Density 0.198%

    No Known Activations