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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 7-RES-JB
    6. 16962
    Prev
    Next
    INDEX
    Explanations

    medical terms related to trauma and healthcare

    oai_token-act-pair · gpt-3.5-turbo

    terms related to trauma and various legal or regulatory frameworks

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    imeters
    -0.75
     carbohyd
    -0.74
     ferment
    -0.73
     nursing
    -0.72
    etheless
    -0.70
    elled
    -0.70
    ulin
    -0.69
     suburbs
    -0.69
     whisk
    -0.69
    unts
    -0.66
    POSITIVE LOGITS
     Therapy
    1.02
     Opportun
    1.02
     Integrity
    1.01
    Gate
    1.00
     Clause
    0.99
     Dynamics
    0.98
     Direction
    0.96
     Accountability
    0.94
     Awareness
    0.94
     Prevention
    0.92
    Activations Density 0.392%

    No Known Activations