© 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. 1-RES-JB
    11. 16404
    Prev
    Next
    INDEX
    Explanations

    references to institutions or entities with the word "Royal" in their name

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the word "Royal" related to institutions, organizations, or entities

    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
    icago
    -0.74
    ARB
    -0.73
     Fas
    -0.71
    CRIP
    -0.67
    ones
    -0.67
    lr
    -0.66
    EEK
    -0.65
    é¾į
    -0.65
    printf
    -0.64
     Gutenberg
    -0.63
    POSITIVE LOGITS
     Royal
    1.06
    Royal
    0.93
     Palace
    0.89
    uese
    0.80
    tarian
    0.79
     monarchy
    0.78
     mosqu
    0.77
     aristocracy
    0.75
     royal
    0.74
     satell
    0.73
    Activations Density 0.011%

    No Known Activations