© 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. 10-RES-JB
    11. 2835
    Prev
    Next
    INDEX
    Explanations

    mentions of the word "Ignatius"

    oai_token-act-pair · gpt-3.5-turbo

    the concept of ignorance and related terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    CHAT
    -0.69
    76561
    -0.69
    scenes
    -0.67
    bian
    -0.66
    grass
    -0.64
     Tale
    -0.63
    TON
    -0.63
    EStream
    -0.62
     Morph
    -0.62
    pants
    -0.61
    POSITIVE LOGITS
    oreAnd
    1.31
    acio
    1.28
    oring
    1.22
    orable
    1.20
    ition
    1.20
    iting
    1.10
    omin
    1.10
    ores
    1.08
    itable
    1.07
    ited
    1.04
    Activations Density 0.024%

    No Known Activations