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

    Neuronpedia

    Jacobian LensNEW
    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. 4-RES-JB
    11. 901
    Prev
    Next
    INDEX
    Explanations

    mentions of inflammatory responses or conditions related to inflammation

    oai_token-act-pair · gpt-3.5-turbo

    terms related to inflammation and its effects on health

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

    No Comments

    Negative Logits
    ģĸ
    -0.86
    itto
    -0.76
    hare
    -0.75
    ibling
    -0.75
    Ü
    -0.74
    fman
    -0.74
    anooga
    -0.72
    aucus
    -0.71
    etheus
    -0.71
    ault
    -0.69
    POSITIVE LOGITS
     cytok
    1.19
     bowel
    0.96
     inflammation
    0.93
     infiltrate
    0.93
     arthritis
    0.92
    lamm
    0.91
     inflammatory
    0.88
    inflammatory
    0.85
     irrit
    0.84
     inflamm
    0.82
    Activations Density 0.021%

    No Known Activations