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

    Neuronpedia

    APISteerSAE EvalsBlog/PodcastNEWSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 5-RES-JB
    6. 8753
    Prev
    Next
    INDEX
    Explanations

    phrases related to romantic or sexual relationships

    oai_token-act-pair · gpt-3.5-turbo

    terms related to extramarital affairs and domestic violence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    £ı
    -0.81
     Siem
    -0.72
    Downloadha
    -0.71
    akeru
    -0.69
    æ©Ł
    -0.69
     lawy
    -0.68
     chalk
    -0.67
     Flavoring
    -0.66
     Canaver
    -0.66
     grading
    -0.65
    POSITIVE LOGITS
     affair
    0.96
     marry
    0.91
     sex
    0.90
    riages
    0.90
     monog
    0.90
    arenthood
    0.88
     virginity
    0.88
    marriage
    0.87
     adultery
    0.84
     divorce
    0.84
    Activations Density 0.224%

    No Known Activations