© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 429
    Prev
    Next
    INDEX
    Explanations

    keywords related to romantic relationships

    oai_token-act-pair · gpt-3.5-turbo

    the word stem "rom" as in romance or romantic, but can occasionally confuse it with acronyms like "ROM" in different contexts

    oai_token-act-pair · gpt-4-turbo

    content related to romance or romantic themes

    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
    Ĥ¬
    -0.73
    Ùĩ
    -0.70
    avanaugh
    -0.68
    Reviewer
    -0.68
     lack
    -0.64
     administering
    -0.64
     Rouhani
    -0.62
     Lotus
    -0.62
    DIT
    -0.60
    gettable
    -0.60
    POSITIVE LOGITS
    antically
    1.05
    aji
    0.99
    pton
    0.91
    ancing
    0.85
    ucci
    0.85
    agra
    0.83
    ances
    0.82
    agers
    0.79
    andal
    0.79
    aine
    0.79
    Activations Density 0.004%

    No Known Activations