© 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. 10085
    Prev
    Next
    INDEX
    Explanations

    mentions of political independence and related events

    oai_token-act-pair · gpt-3.5-turbo

    mentions of independence and independence referendums

    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
    bilt
    -0.83
    enegger
    -0.80
    geon
    -0.71
     Insect
    -0.69
    onz
    -0.67
    eger
    -0.66
    nos
    -0.66
    geries
    -0.65
    aceae
    -0.64
    azard
    -0.64
    POSITIVE LOGITS
     referendum
    1.15
     refere
    0.83
     struggle
    0.80
     campaigners
    0.77
     oath
    0.77
     movement
    0.76
     declaration
    0.75
     Catalonia
    0.74
     campaigner
    0.73
     ballot
    0.73
    Activations Density 0.058%

    No Known Activations