© 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. 11311
    Prev
    Next
    INDEX
    Explanations

    mentions of Scottish-related entities or activities

    oai_token-act-pair · gpt-3.5-turbo

    mentions of Scotland and related political entities

    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
    ysis
    -1.02
    igslist
    -0.79
     tremend
    -0.76
    pread
    -0.75
    sites
    -0.73
    eus
    -0.70
    ĸļ
    -0.70
     Fresno
    -0.69
    advertising
    -0.67
    hou
    -0.67
    POSITIVE LOGITS
     Yard
    1.44
     Gael
    1.31
     Rite
    1.14
     Premiership
    1.07
    Scotland
    1.05
     Highlands
    1.03
     Scots
    1.02
     Scotland
    1.02
     independence
    1.00
     Parliament
    1.00
    Activations Density 0.039%

    No Known Activations