© 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
    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. 24056
    Prev
    Next
    INDEX
    Explanations

    keywords related to technology products and services

    oai_token-act-pair · gpt-3.5-turbo

    technical terms and names related to mobile devices or applications

    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
    SPONSORED
    -0.59
     wealthier
    -0.58
     predec
    -0.57
     prevailing
    -0.56
     customary
    -0.56
    ×ŀ
    -0.55
     wealthy
    -0.55
     psychiat
    -0.55
     arrang
    -0.54
    sit
    -0.54
    POSITIVE LOGITS
     Profile
    1.23
    âĦ¢
    0.80
    ®
    0.79
     Presents
    0.78
    âĦ¢:
    0.78
     Calculator
    0.78
     Reloaded
    0.77
     Originally
    0.77
     Plugin
    0.77
     âĵĺ
    0.77
    Activations Density 0.474%

    No Known Activations