© 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. 0-RES-JB
    11. 5398
    Prev
    Next
    INDEX
    Explanations

    mentions of royalty or princesses

    oai_token-act-pair · gpt-3.5-turbo

    references to "Princess" and related terms

    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
    iasm
    -0.76
    iton
    -0.73
     fiber
    -0.64
    ional
    -0.64
    abi
    -0.64
     Weber
    -0.62
     eval
    -0.61
     modem
    -0.60
    ab
    -0.60
     defense
    -0.59
    POSITIVE LOGITS
     Princess
    3.81
     princess
    2.53
    Prin
    2.30
     Duchess
    1.92
     Empress
    1.73
     Prince
    1.69
     Queen
    1.61
    Prince
    1.58
     Goddess
    1.57
     Sorceress
    1.51
    Activations Density 0.014%

    No Known Activations