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. 10-RES-JB
    6. 20137
    Prev
    Next
    INDEX
    Explanations

    information related to Scotland's relationship with the European Union and the United Kingdom

    oai_token-act-pair · gpt-3.5-turbo

    references to Scotland's political status and independence discussions

    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
     Nguyen
    -1.05
     Cambod
    -1.02
     Droid
    -1.00
     Mek
    -1.00
     NYPD
    -0.96
     Liang
    -0.95
    guyen
    -0.94
     Zhou
    -0.93
     Mei
    -0.93
     Vietnamese
    -0.93
    POSITIVE LOGITS
     Scottish
    2.21
     Scotland
    2.16
     Scots
    2.10
    Scotland
    2.05
     SNP
    1.99
     Edinburgh
    1.82
     Sturgeon
    1.81
     Glasgow
    1.68
     Aberdeen
    1.60
     Nicola
    1.58
    Activations Density 0.322%

    No Known Activations