© 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. 13821
    Prev
    Next
    INDEX
    Explanations

    phrases related to technology and data analysis

    oai_token-act-pair · gpt-3.5-turbo

    features and functionalities related to health assessment and metrics in 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
     Forsaken
    -0.75
     Variant
    -0.70
     Tradition
    -0.68
    ominated
    -0.67
     Canaver
    -0.66
     Sacrifice
    -0.66
     Creed
    -0.66
    bare
    -0.64
     Argument
    -0.64
     McDonnell
    -0.63
    POSITIVE LOGITS
     alerts
    1.56
     pinpoint
    1.39
     alert
    1.33
     monitoring
    1.32
     tracking
    1.30
     predictive
    1.24
    Alert
    1.24
     monitor
    1.23
     alerted
    1.18
     reminders
    1.17
    Activations Density 0.556%

    No Known Activations