© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 1-RES-JB
    6. 21178
    Prev
    Next
    INDEX
    Explanations

    words related to old-fashioned language, particularly 'thou', 'thee', and 'thy'

    oai_token-act-pair · gpt-3.5-turbo

    archaic pronouns and related forms of address

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    eteria
    -0.84
    eland
    -0.78
    enhagen
    -0.72
     Eisen
    -0.72
    VG
    -0.72
    olina
    -0.72
    EEK
    -0.71
    inctions
    -0.71
    enthal
    -0.70
    IDENT
    -0.70
    POSITIVE LOGITS
     Thou
    1.37
     thou
    1.37
     shalt
    1.16
     thy
    0.96
     thee
    0.90
     compr
    0.84
     Thy
    0.83
    ggles
    0.80
     distingu
    0.75
    \\\\\\\\
    0.73
    Activations Density 0.012%

    No Known Activations