© 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. 8-RES-JB
    11. 17869
    Prev
    Next
    INDEX
    Explanations

    medical terms or other terms related to healthcare and infrastructure systems

    oai_token-act-pair · gpt-3.5-turbo

    references to primary care and related healthcare concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    uge
    -0.79
    estern
    -0.77
     Doodle
    -0.72
    âĸĪâĸĪ
    -0.69
     Feet
    -0.68
    phis
    -0.68
    uu
    -0.68
    LER
    -0.67
    terness
    -0.67
    INESS
    -0.67
    POSITIVE LOGITS
     careg
    0.98
    tenance
    0.87
     beneficiary
    0.83
     antagonist
    0.82
     caregivers
    0.81
     outcome
    0.77
     residences
    0.76
     distingu
    0.76
    iary
    0.75
     culprit
    0.75
    Activations Density 0.024%

    No Known Activations