© 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. 10-RES-JB
    11. 7177
    Prev
    Next
    INDEX
    Explanations

    words related to medical conditions, particularly respiratory and metabolic issues

    oai_token-act-pair · gpt-3.5-turbo

    terms related to respiratory and cardiovascular health issues

    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
    imately
    -0.88
    cham
    -0.81
    tower
    -0.81
    igun
    -0.79
    lessly
    -0.76
    urat
    -0.76
    hole
    -0.75
    chin
    -0.75
    atz
    -0.75
    awaru
    -0.75
    POSITIVE LOGITS
     distress
    1.05
     disturbances
    1.04
     disturbance
    0.94
     stimuli
    0.93
     stimulation
    0.93
     anomalies
    0.91
     profiling
    0.90
     integrity
    0.89
     dysfunction
    0.87
     arousal
    0.87
    Activations Density 0.084%

    No Known Activations