© 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. 11-RES-JB
    11. 7762
    Prev
    Next
    INDEX
    Explanations

    words related to seduction and enticement

    oai_token-act-pair · gpt-3.5-turbo

    instances and variations of the word "seduce" and related concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    BY
    -0.74
    sticks
    -0.62
    balls
    -0.62
    starter
    -0.61
    ball
    -0.58
     Boy
    -0.58
    Magn
    -0.58
     Briggs
    -0.57
     PIT
    -0.57
    #$
    -0.55
    POSITIVE LOGITS
    entary
    1.79
    uctive
    1.78
    uction
    1.61
    uct
    1.52
    uctions
    1.51
    ucing
    1.42
    itious
    1.42
    uced
    1.38
    ucer
    1.38
    uce
    1.29
    Activations Density 0.046%

    No Known Activations