© 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. 1-RES-JB
    11. 3702
    Prev
    Next
    INDEX
    Explanations

    phrases using the word "unto"

    oai_token-act-pair · gpt-3.5-turbo

    phrases that convey a sense of religious or archaic authority

    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
    orno
    -0.75
    packing
    -0.72
    orescent
    -0.72
    employed
    -0.71
    eways
    -0.70
    groups
    -0.69
    ritz
    -0.69
    iple
    -0.68
    Journal
    -0.67
    lining
    -0.67
    POSITIVE LOGITS
     unto
    1.13
     thee
    0.85
     behold
    0.77
     Hath
    0.76
    hovah
    0.76
     hath
    0.72
    rontal
    0.72
     thy
    0.72
     conclud
    0.69
     shalt
    0.69
    Activations Density 0.007%

    No Known Activations