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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 11-RES-JB
    6. 17620
    Prev
    Next
    INDEX
    Explanations

    technical and business-related terms and entities related to different industries such as technology, finance, and gaming

    oai_token-act-pair · gpt-3.5-turbo

    references to technology and business-related entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     weakest
    -0.71
    enegger
    -0.70
     settlements
    -0.69
     reintrodu
    -0.68
     canoe
    -0.66
     gar
    -0.66
     apes
    -0.65
     brunt
    -0.64
     kissing
    -0.63
     baggage
    -0.63
    POSITIVE LOGITS
    Week
    1.12
    Daily
    1.12
    News
    1.12
    Wire
    1.09
    Times
    1.07
    Beat
    1.05
    Business
    1.03
    Techn
    1.03
    Politics
    1.01
    Press
    1.00
    Activations Density 0.189%

    No Known Activations