© 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. 2-RES-JB
    6. 10402
    Prev
    Next
    INDEX
    Explanations

    words related to faithfulness or loyalty

    oai_token-act-pair · gpt-3.5-turbo

    themes related to faithfulness and commitment

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    NetMessage
    -0.78
    Han
    -0.75
    AAF
    -0.75
     Marketable
    -0.74
    ISM
    -0.69
    ORGE
    -0.68
    Sing
    -0.67
    #$#$
    -0.67
     Aden
    -0.67
    asta
    -0.66
    POSITIVE LOGITS
     faithful
    1.12
    atile
    0.90
    iciary
    0.85
     worsh
    0.83
    sembly
    0.81
     servant
    0.81
     adherence
    0.81
     fidelity
    0.80
    itiz
    0.80
    aith
    0.78
    Activations Density 0.011%

    No Known Activations