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

    Neuronpedia

    APICircuit 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. 3-RES-JB
    6. 2382
    Prev
    Next
    INDEX
    Explanations

    information related to demographics and statistics

    oai_token-act-pair · gpt-3.5-turbo

    references to demographic groups and their statistical characteristics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     pus
    -0.84
    £ı
    -0.81
    USS
    -0.79
    DragonMagazine
    -0.74
    ffic
    -0.72
     apologise
    -0.71
    UTH
    -0.71
    ulence
    -0.71
    elight
    -0.70
    emonium
    -0.70
    POSITIVE LOGITS
     households
    1.08
     Disability
    1.07
     retirees
    0.98
     incomes
    0.96
     uninsured
    0.95
     literacy
    0.94
     Millennials
    0.92
     Unemployment
    0.92
     Median
    0.91
     births
    0.91
    Activations Density 0.913%

    No Known Activations