© 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. 3-RES-JB
    11. 3304
    Prev
    Next
    INDEX
    Explanations

    locations or entities related to the term "Rapids"

    oai_token-act-pair · gpt-3.5-turbo

    names associated with specific locations and notable individuals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    atu
    -0.85
    mare
    -0.84
    lihood
    -0.79
    orously
    -0.78
    orial
    -0.71
    mong
    -0.70
    mares
    -0.69
    uala
    -0.69
    uchin
    -0.68
    ritional
    -0.67
    POSITIVE LOGITS
     Rapids
    0.98
    Store
    0.76
    paces
    0.73
    Constructed
    0.67
    é£
    0.67
    fruit
    0.65
    ISO
    0.64
    Denver
    0.64
    Blocks
    0.63
    inence
    0.62
    Activations Density 0.010%

    No Known Activations