© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 10-RES-JB
    11. 17356
    Prev
    Next
    INDEX
    Explanations

    phrases related to health conditions and medical risk factors

    oai_token-act-pair · gpt-3.5-turbo

    terms related to health risk assessments and smoking cessation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    fuck
    -0.92
    Lenin
    -0.92
    Marx
    -0.90
     Trotsky
    -0.87
    shit
    -0.86
    acas
    -0.82
     Syndicate
    -0.81
    Hell
    -0.79
     Shards
    -0.78
     Bits
    -0.77
    POSITIVE LOGITS
     preventive
    1.60
     clinicians
    1.55
     prevention
    1.54
     prescribing
    1.47
     pediatric
    1.36
     vaccination
    1.35
     physicians
    1.35
     interventions
    1.30
     prenatal
    1.30
     medications
    1.27
    Activations Density 0.551%

    No Known Activations