© 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. 3-RES-JB
    11. 10729
    Prev
    Next
    INDEX
    Explanations

    references to entities associated with the word "Royal."

    oai_token-act-pair · gpt-3.5-turbo

    the term "Royal" in various contexts and references

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Gutenberg
    -0.86
    icago
    -0.77
    orer
    -0.76
    é¾į
    -0.71
    EEK
    -0.70
    mble
    -0.67
     Remastered
    -0.67
     Canaver
    -0.66
    printf
    -0.66
    ARB
    -0.65
    POSITIVE LOGITS
    ty
    0.89
     Palace
    0.89
     Arabia
    0.84
     Royal
    0.83
    Royal
    0.75
    ston
    0.73
     Jordanian
    0.71
     jelly
    0.70
     Guard
    0.70
     Rumble
    0.70
    Activations Density 0.011%

    No Known Activations