© 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. 2-RES-JB
    11. 17521
    Prev
    Next
    INDEX
    Explanations

    words related to supporting, maintaining, or preserving something, especially in a legal or moral context

    oai_token-act-pair · gpt-3.5-turbo

    words and phrases related to upholding laws or principles

    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
    ohydrate
    -0.73
    apter
    -0.72
    NetMessage
    -0.72
    Leary
    -0.69
    ones
    -0.64
     NCT
    -0.63
    goo
    -0.63
    Stock
    -0.63
    pox
    -0.63
    GER
    -0.60
    POSITIVE LOGITS
     upholding
    0.97
     upheld
    0.93
     uphold
    0.86
    enance
    0.84
    orius
    0.80
     Reincarn
    0.75
    raint
    0.73
     rul
    0.72
    folios
    0.72
    raints
    0.70
    Activations Density 0.007%

    No Known Activations