© 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. 2-RES-JB
    11. 23585
    Prev
    Next
    INDEX
    Explanations

    phrases related to medical conditions and body parts in the context of blood circulation and diseases

    oai_token-act-pair · gpt-3.5-turbo

    terms related to blood and cardiovascular health

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    DragonMagazine
    -0.88
    女
    -0.82
    Merit
    -0.80
    rawdownloadcloneembedreportprint
    -0.78
    =-=-
    -0.78
    htaking
    -0.77
    Priv
    -0.75
    Artist
    -0.75
    HOU
    -0.71
    Sund
    -0.69
    POSITIVE LOGITS
     inflammation
    1.18
     disorders
    1.11
     cardiovascular
    0.98
     stimulation
    0.94
     adip
    0.92
     cardiac
    0.91
     biomark
    0.91
     abnormalities
    0.90
     lymph
    0.90
     tissue
    0.90
    Activations Density 0.328%

    No Known Activations