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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 9-RES-JB
    6. 10634
    Prev
    Next
    INDEX
    Explanations

    mentions of individuals with specific age descriptions

    oai_token-act-pair · gpt-3.5-turbo

    references to age, specifically indicating the age of individuals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    rats
    -0.95
    ©¶æ
    -0.88
    ËĪ
    -0.84
    oldown
    -0.84
    ģĸ
    -0.83
    orses
    -0.81
    ipedia
    -0.80
    TPP
    -0.79
    mbuds
    -0.77
    ascript
    -0.77
    POSITIVE LOGITS
     Frenchman
    0.93
     woman
    0.92
     widow
    0.89
     accountant
    0.85
     man
    0.80
     millionaire
    0.79
     wid
    0.79
     grandmother
    0.75
     female
    0.74
     male
    0.74
    Activations Density 0.050%

    No Known Activations