© 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. 0-RES-JB
    11. 9494
    Prev
    Next
    INDEX
    Explanations

    phrases related to medical settings or treatments

    oai_token-act-pair · gpt-3.5-turbo

    references to hospitals and hospital-related contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    bits
    -0.77
    arius
    -0.65
     Tactics
    -0.64
    使
    -0.63
     Sphere
    -0.62
     âľĶ
    -0.61
    lance
    -0.61
    liners
    -0.61
     Modes
    -0.61
     Stack
    -0.61
    POSITIVE LOGITS
     hospital
    3.53
     hospitals
    2.53
     Hospital
    2.48
    hospital
    2.37
    ospital
    2.10
     hospitalized
    1.91
     Hosp
    1.86
     ambulance
    1.80
     clinic
    1.78
     nurses
    1.73
    Activations Density 0.022%

    No Known Activations