© 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. 0-RES-JB
    11. 8258
    Prev
    Next
    INDEX
    Explanations

    the adjective "loyal" used to describe individuals

    oai_token-act-pair · gpt-3.5-turbo

    instances of the term "loyal" and its variations in different contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    eco
    -0.77
    AGE
    -0.72
    AIDS
    -0.70
    ø
    -0.69
    iframe
    -0.68
    STEM
    -0.66
    ODY
    -0.65
    ures
    -0.64
     CASE
    -0.64
    URES
    -0.63
    POSITIVE LOGITS
     loyal
    3.89
     Loyal
    2.03
    oyal
    1.96
     loyalty
    1.91
     faithful
    1.65
     obedient
    1.55
     devoted
    1.29
     allegiance
    1.26
     rabid
    1.20
     ardent
    1.17
    Activations Density 0.016%

    No Known Activations