© 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. 674
    Prev
    Next
    INDEX
    Explanations

    phrases containing the word "iri."

    oai_token-act-pair · gpt-3.5-turbo

    the occurrence of the term "iri" in various contexts

    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
    egg
    -0.78
    spin
    -0.76
    bags
    -0.68
    size
    -0.65
     Insect
    -0.64
    log
    -0.64
     Libertarian
    -0.64
    rooms
    -0.63
    products
    -0.62
    meal
    -0.61
    POSITIVE LOGITS
    yah
    1.03
    ya
    1.01
    iri
    0.93
    oux
    0.87
    uddy
    0.86
    ova
    0.86
    azo
    0.85
    ón
    0.84
    osa
    0.84
    orno
    0.83
    Activations Density 0.009%

    No Known Activations