© 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. 7704
    Prev
    Next
    INDEX
    Explanations

    terms related to faithfulness and commitment

    oai_token-act-pair · gpt-3.5-turbo

    concepts related to loyalty and faithfulness

    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
    ask
    -0.78
    ode
    -0.67
    hops
    -0.65
     Definitions
    -0.63
    NetMessage
    -0.63
    ITIES
    -0.62
    oder
    -0.60
    ities
    -0.59
    ocy
    -0.58
    yson
    -0.58
    POSITIVE LOGITS
     faithful
    3.92
     faithfully
    1.83
     loyal
    1.63
    faith
    1.31
     fidelity
    1.27
     obedient
    1.25
     devout
    1.19
     believers
    1.18
     pious
    1.17
     Faith
    1.15
    Activations Density 0.015%

    No Known Activations