© 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. 3-RES-JB
    11. 626
    Prev
    Next
    INDEX
    Explanations

    instances related to strong commitment or loyalty to a cause or person

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "dedication" and related terms that express commitment or devotion

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Ther
    -0.71
     Sabha
    -0.70
     Zucker
    -0.70
    Law
    -0.69
     Kahn
    -0.66
    Lev
    -0.66
     Stras
    -0.65
     Spoiler
    -0.65
     supra
    -0.64
    adish
    -0.64
    POSITIVE LOGITS
     dedication
    1.10
     devotion
    0.96
    mble
    0.87
    itiz
    0.84
    rifice
    0.84
    cellence
    0.83
    xual
    0.83
    smanship
    0.82
    spection
    0.81
    anguage
    0.80
    Activations Density 0.010%

    No Known Activations