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

    Neuronpedia

    APICircuit 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. 6-RES-JB
    6. 10140
    Prev
    Next
    INDEX
    Explanations

    references to royalty or princesses

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the word "Princess."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     grate
    -0.67
    sych
    -0.66
     neur
    -0.66
    oker
    -0.65
     smoker
    -0.65
     spaced
    -0.64
     funn
    -0.63
    OUT
    -0.62
    appa
    -0.62
    ulhu
    -0.62
    POSITIVE LOGITS
     Leia
    1.10
     Princess
    1.01
     Diana
    1.01
     Bride
    1.00
     Celest
    0.99
    anova
    0.93
     Peach
    0.87
     princess
    0.86
     Fiona
    0.83
    cess
    0.82
    Activations Density 0.019%

    No Known Activations