© 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. 7-RES-JB
    11. 21133
    Prev
    Next
    INDEX
    Explanations

    phrases related to finding or having a mate

    oai_token-act-pair · gpt-3.5-turbo

    references to companionship or romantic relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    kefeller
    -0.80
    icum
    -0.80
    acea
    -0.70
    GER
    -0.69
    SIGN
    -0.69
    shire
    -0.68
    english
    -0.68
    acco
    -0.66
    lich
    -0.66
    icity
    -0.64
    POSITIVE LOGITS
     mate
    0.91
     Mate
    0.86
     mates
    0.83
     versa
    0.75
    mates
    0.75
    vich
    0.74
    mares
    0.70
    mate
    0.70
    atu
    0.68
    zees
    0.66
    Activations Density 0.032%

    No Known Activations