© 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. 18721
    Prev
    Next
    INDEX
    Explanations

    terms related to specific job titles or roles, such as "press secretary," "culture secretary," and "Regional Coordinator."

    oai_token-act-pair · gpt-3.5-turbo

    titles and roles related to professional positions or job titles

    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
     Invalid
    -0.70
    STDOUT
    -0.70
     Publishers
    -0.68
    Sources
    -0.66
    ij
    -0.65
    اÙĦ
    -0.65
    Parser
    -0.63
    ±
    -0.62
    Īè
    -0.60
    ģĸ
    -0.59
    POSITIVE LOGITS
    ial
    1.22
    ship
    1.13
    SHIP
    1.08
    's
    1.07
    ially
    1.07
    ials
    1.05
    stration
    1.03
    hood
    0.97
    iate
    0.96
     persona
    0.91
    Activations Density 0.397%

    No Known Activations