© 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. 7-RES-JB
    11. 12542
    Prev
    Next
    INDEX
    Explanations

    phrases related to health issues and medical conditions

    oai_token-act-pair · gpt-3.5-turbo

    references to medical conditions and health-related issues

    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
     bidding
    -0.79
     barg
    -0.78
     patriotism
    -0.78
     treasury
    -0.77
    itage
    -0.76
     loyalty
    -0.75
     pivot
    -0.74
    azon
    -0.74
    enaries
    -0.74
     mercenary
    -0.73
    POSITIVE LOGITS
     Symptoms
    1.51
     Diseases
    1.24
    Sym
    1.13
     Researchers
    1.12
    Researchers
    1.12
     Pediatrics
    1.11
    Studies
    1.10
    ptoms
    1.10
    Scientists
    1.08
     Patients
    1.06
    Activations Density 0.640%

    No Known Activations