© 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. 2373
    Prev
    Next
    INDEX
    Explanations

    words related to sexual abuse and misconduct

    oai_token-act-pair · gpt-3.5-turbo

    references to sexual offenses and abuses involving minors

    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
    cation
    -0.80
    mort
    -0.68
    iHUD
    -0.68
    ovation
    -0.67
    fen
    -0.66
    ghai
    -0.66
    terday
    -0.65
     attRot
    -0.64
    ãĥ¯ãĥ³
    -0.63
    inventoryQuantity
    -0.63
    POSITIVE LOGITS
     underage
    1.53
     minors
    1.29
     prostitutes
    1.24
     girls
    1.18
    girlfriend
    1.16
     teenage
    1.12
     prostitute
    1.11
     females
    1.08
     female
    1.04
     girlfriends
    1.03
    Activations Density 0.249%

    No Known Activations