© 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. 10-RES-JB
    11. 18613
    Prev
    Next
    INDEX
    Explanations

    names of historical figures and royal titles

    oai_token-act-pair · gpt-3.5-turbo

    historical figures and events related to monarchy

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    malink
    -0.82
    ratom
    -0.81
    tools
    -0.76
    reporting
    -0.76
     takeaway
    -0.75
    FOX
    -0.75
     clip
    -0.74
    taboola
    -0.73
    GAN
    -0.73
     trending
    -0.72
    POSITIVE LOGITS
     XVI
    1.41
     Augustus
    1.36
     XIV
    1.35
     VIII
    1.34
     VII
    1.29
     XII
    1.21
     Tud
    1.18
     XIII
    1.17
     XV
    1.11
     Ferdinand
    1.10
    Activations Density 0.159%

    No Known Activations