© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 0-RES-JB
    11. 22594
    Prev
    Next
    INDEX
    Explanations

    phrases related to legal proceedings involving the term "Crown"

    oai_token-act-pair · gpt-3.5-turbo

    references to the term "Crown."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    etta
    -0.70
    lat
    -0.67
    lov
    -0.64
    asm
    -0.62
     steril
    -0.62
    fl
    -0.62
     isol
    -0.61
    ASY
    -0.61
     newsletters
    -0.61
     kernels
    -0.61
    POSITIVE LOGITS
     Crown
    4.09
     crown
    2.38
    rown
    1.39
     Crest
    1.17
     throne
    1.12
     Majesty
    1.12
     Crom
    1.12
     Monarch
    1.11
     Royal
    1.07
     coron
    1.06
    Activations Density 0.012%

    No Known Activations