© 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. 8-RES-JB
    11. 7779
    Prev
    Next
    INDEX
    Explanations

    references to the word "Liberty"

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the word "Liberty" and its variations or related contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    •single token firings
    Individually fires on " Millennium", " Liberty", " Century", " victory", ...

    No Comments

    Negative Logits
    eware
    -0.92
    orders
    -0.88
    oshop
    -0.84
    nesses
    -0.83
    odynam
    -0.80
    otton
    -0.79
    ets
    -0.78
    elist
    -0.77
    avid
    -0.77
    haps
    -0.76
    POSITIVE LOGITS
     Broadcasting
    1.09
     Beach
    1.04
     Boulevard
    1.04
     Heights
    1.02
     Hills
    1.02
     Park
    1.00
     Valley
    1.00
     Crest
    0.99
     Oaks
    0.98
     Downs
    0.97
    Activations Density 0.220%

    No Known Activations