© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 10-RES-JB
    11. 13853
    Prev
    Next
    INDEX
    Explanations

    statistical and numerical data related to demographics and healthcare

    oai_token-act-pair · gpt-3.5-turbo

    numerical statistics related to health and demographic data

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    htaking
    -0.64
     perks
    -0.63
    theless
    -0.61
    oward
    -0.59
     Emblem
    -0.59
     reluct
    -0.58
    arde
    -0.57
    agnar
    -0.57
    Quotes
    -0.57
    oiler
    -0.57
    POSITIVE LOGITS
     inhabitants
    0.92
     population
    0.86
     capita
    0.86
     squared
    0.82
     Dwell
    0.78
     residents
    0.76
    ãĤ¼ãĤ¦ãĤ¹
    0.76
     Population
    0.74
     cubic
    0.73
    dL
    0.72
    Activations Density 0.089%

    No Known Activations