Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 1-RES-JB
    6. 4165
    Prev
    Next
    INDEX
    Explanations

    references to royalty figures, particularly princes and princesses

    oai_token-act-pair · gpt-3.5-turbo

    references to royal titles, specifically those associated with princes and princesses

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    veyard
    -0.84
     Caption
    -0.81
     Haas
    -0.80
     Methods
    -0.73
     Parenthood
    -0.72
     Yards
    -0.71
    KT
    -0.71
     Brewer
    -0.69
     Vehicles
    -0.68
     Telephone
    -0.68
    POSITIVE LOGITS
     prince
    1.31
     princes
    1.04
     princess
    1.00
    doms
    0.89
    loo
    0.81
    esses
    0.79
    lings
    0.79
    pin
    0.79
     pengu
    0.78
    men
    0.76
    Activations Density 0.014%

    No Known Activations