© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 11-RES-JB
    6. 6738
    Prev
    Next
    INDEX
    Explanations

    mentions of the name "Ignatius."

    oai_token-act-pair · gpt-3.5-turbo

    references to "Ignatius."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    bian
    -0.82
    scenes
    -0.66
    --------------------------------------------------------
    -0.65
    plane
    -0.64
    layer
    -0.63
     Jiu
    -0.62
    planes
    -0.62
     Shard
    -0.61
    ------------------------------------------------
    -0.59
    lings
    -0.58
    POSITIVE LOGITS
    oreAnd
    1.44
    orable
    1.34
    ition
    1.25
    acio
    1.21
    ited
    1.13
    oring
    1.11
    ores
    1.10
    omin
    1.07
    essee
    1.07
    ored
    1.05
    Activations Density 0.041%

    No Known Activations