© 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. 2-RES-JB
    11. 3123
    Prev
    Next
    INDEX
    Explanations

    words related to professions or fields, specifically focusing on military, medical, traditional, and technological terms

    oai_token-act-pair · gpt-3.5-turbo

    terms related to military and affiliations, including various types of communities and activities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     blister
    -0.70
     immediate
    -0.66
     powerful
    -0.65
     overcrowd
    -0.64
     generous
    -0.63
     tens
    -0.62
     valuable
    -0.61
     liv
    -0.61
     mighty
    -0.61
     swell
    -0.61
    POSITIVE LOGITS
    theless
    1.55
    tenance
    1.44
    terday
    1.37
    etheless
    1.04
    DragonMagazine
    1.00
    odore
    0.95
    iculty
    0.90
    CLASSIFIED
    0.89
    lihood
    0.88
    ãĤ´ãĥ³
    0.88
    Activations Density 0.313%

    No Known Activations