© 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. 17703
    Prev
    Next
    INDEX
    Explanations

    terms related to loyalty, commitment, and allegiance

    oai_token-act-pair · gpt-3.5-turbo

    references to loyalty

    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
    Not in Any Lists

    No Comments

    Negative Logits
    quick
    -0.68
     concussion
    -0.64
    paces
    -0.62
    hazard
    -0.61
     Apocalypse
    -0.59
    phrine
    -0.59
    LOD
    -0.58
    annis
    -0.58
    osed
    -0.58
    _-
    -0.57
    POSITIVE LOGITS
     allegiance
    1.01
    ty
    0.98
     loyal
    0.91
    ties
    0.91
    alty
    0.91
     loyalty
    0.91
     oath
    0.87
    alties
    0.84
    hips
    0.83
    eness
    0.81
    Activations Density 0.045%

    No Known Activations