Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 6-RES-JB
    6. 16695
    Prev
    Next
    INDEX
    Explanations

    phrases related to sexual assault and misconduct

    oai_token-act-pair · gpt-3.5-turbo

    instances of sexual offenses and related legal terminology

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     guiActiveUnfocused
    -0.80
    inventoryQuantity
    -0.73
     cancell
    -0.73
    Weather
    -0.72
    pmwiki
    -0.71
    ocus
    -0.71
     Aerospace
    -0.70
    akings
    -0.69
    HUD
    -0.68
    icip
    -0.67
    POSITIVE LOGITS
    girlfriend
    1.03
     underage
    0.96
     prostitutes
    0.95
     genitals
    0.94
     classmate
    0.92
     breasts
    0.91
     girlfriend
    0.91
     prostitute
    0.88
     innocent
    0.88
     boyfriend
    0.88
    Activations Density 0.236%

    No Known Activations