© 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. 1-RES-JB
    11. 24308
    Prev
    Next
    INDEX
    Explanations

    references to the word "unpasteurized."

    oai_token-act-pair · gpt-3.5-turbo

    terms related to being unpasteurized or unprocessed

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Carbuncle
    -0.76
    ulu
    -0.75
     Lauder
    -0.74
     Rams
    -0.73
    quickShipAvailable
    -0.73
    tone
    -0.68
     Engineers
    -0.68
    姫
    -0.66
    gio
    -0.65
     Dynamics
    -0.64
    POSITIVE LOGITS
     unp
    1.45
    aired
    0.94
    iqu
    0.94
    isexual
    0.86
    ainted
    0.85
    assuming
    0.85
     unch
    0.85
    orter
    0.85
    aste
    0.83
    ishable
    0.83
    Activations Density 0.006%

    No Known Activations