© 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. 3-RES-JB
    11. 15806
    Prev
    Next
    INDEX
    Explanations

    topics related to social and political issues, including legislation, medical care, diversity, surveillance, and transportation regulations

    oai_token-act-pair · gpt-3.5-turbo

    terms related to political and social issues, particularly around rights, legislation, and societal challenges

    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
    soDeliveryDate
    -0.51
    erker
    -0.50
    ulhu
    -0.47
    ucket
    -0.46
    pherd
    -0.46
    ovie
    -0.45
    utra
    -0.45
    uncle
    -0.45
    arij
    -0.45
    ortium
    -0.45
    POSITIVE LOGITS
    bugs
    0.46
     detainees
    0.43
     probes
    0.43
     purposes
    0.43
     unprepared
    0.42
     eaves
    0.42
     agre
    0.41
     quotas
    0.41
     levels
    0.41
     programming
    0.40
    Activations Density 2.499%

    No Known Activations