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. 8-RES-JB
    6. 4451
    Prev
    Next
    INDEX
    Explanations

    mentions of the number of children someone has

    oai_token-act-pair · gpt-3.5-turbo

    references to familial relationships, especially children

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    pmwiki
    -0.85
    ioxide
    -0.70
     prevailing
    -0.65
     metic
    -0.65
    âĸ¬
    -0.63
     guiActiveUnfocused
    -0.62
     hardness
    -0.59
    thouse
    -0.58
     vitri
    -0.58
    NK
    -0.57
    POSITIVE LOGITS
    riages
    1.05
     grandchildren
    0.98
     inherit
    0.88
    mares
    0.86
    iblings
    0.83
    pins
    0.82
    Eva
    0.80
     daughters
    0.77
     daddy
    0.76
    arenthood
    0.76
    Activations Density 0.088%

    No Known Activations