© 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. 1-RES-JB
    11. 3791
    Prev
    Next
    INDEX
    Explanations

    terms related to upholding principles or laws

    oai_token-act-pair · gpt-3.5-turbo

    words related to maintaining or supporting laws and principles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    NetMessage
    -0.84
    apter
    -0.61
    feet
    -0.61
    ones
    -0.60
    ching
    -0.59
    hoe
    -0.59
    Leary
    -0.59
     Huntington
    -0.58
     Scream
    -0.57
    operated
    -0.57
    POSITIVE LOGITS
     uphold
    1.05
     upholding
    1.00
     upheld
    0.91
    enance
    0.82
    eous
    0.80
    lyak
    0.77
    cies
    0.77
    uph
    0.77
    raints
    0.76
    smanship
    0.75
    Activations Density 0.007%

    No Known Activations