© 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. 12790
    Prev
    Next
    INDEX
    Explanations

    words related to utopia and dystopia

    oai_token-act-pair · gpt-3.5-turbo

    mentions of "utopia" and related terms

    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
     Sins
    -0.72
    Downloadha
    -0.68
    utenant
    -0.66
    naire
    -0.66
    guard
    -0.63
    pmwiki
    -0.63
    ortium
    -0.62
     Defenders
    -0.62
     Dragonbound
    -0.62
    Advertisements
    -0.61
    POSITIVE LOGITS
     ut
    1.11
    hered
    1.04
    tle
    0.96
    ted
    0.91
    eco
    0.90
    terness
    0.89
    ters
    0.84
    cro
    0.84
    zel
    0.83
     ja
    0.83
    Activations Density 0.003%

    No Known Activations