© 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. 8001
    Prev
    Next
    INDEX
    Explanations

    references to the Sons of Liberty, a group historically associated with American Revolution activities

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating possession or association

    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
    •contextual features
    Fires on a connection token in the middle of a name (Sons _of_ Anarchy, Angel _of_ Hope, Mercedez_-_Benz, Statue _of_ Liberty, Alexander _Mc_Queen

    No Comments

    Negative Logits
     commissions
    -0.77
     nails
    -0.71
    enegger
    -0.69
     tumble
    -0.68
    ruary
    -0.66
     cigars
    -0.65
     toll
    -0.64
     CTR
    -0.62
    illac
    -0.60
     funer
    -0.59
    POSITIVE LOGITS
    uria
    0.76
    rette
    0.71
    «ĺ
    0.68
    ciating
    0.65
     monop
    0.63
    umeric
    0.61
    iazep
    0.60
    atar
    0.60
    ãĤ£
    0.59
    ãĥĺ
    0.59
    Activations Density 0.458%

    No Known Activations