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. 9-RES-JB
    6. 15267
    Prev
    Next
    INDEX
    Explanations

    information related to medical conditions and injuries

    oai_token-act-pair · gpt-3.5-turbo

    information related to medical conditions and hospital scenarios

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    soDeliveryDate
    -0.92
    OPA
    -0.79
     hypocr
    -0.75
     contrace
    -0.72
     cheat
    -0.72
     hypocrisy
    -0.71
     infring
    -0.69
     hypocritical
    -0.68
     loophole
    -0.68
     scandals
    -0.66
    POSITIVE LOGITS
     hospital
    1.22
     paramedics
    1.11
     injuries
    1.10
     Hospital
    1.04
     hospitalized
    1.04
     EMS
    1.01
     wounds
    0.99
    EMS
    0.94
     surgery
    0.93
     injured
    0.93
    Activations Density 0.339%

    No Known Activations