© 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. 24525
    Prev
    Next
    INDEX
    Explanations

    keywords related to various topics, such as friendship, movies, quality, industrial complexes, culture, hate crimes, entertainment, education, political processes, franchise, and more

    oai_token-act-pair · gpt-3.5-turbo

    topics related to friendships and relationships

    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
     aven
    -0.96
     senate
    -0.90
     rampant
    -0.89
     muster
    -0.87
     scout
    -0.86
     augmented
    -0.85
     skilled
    -0.85
     disarm
    -0.85
     crest
    -0.85
     displaced
    -0.84
    POSITIVE LOGITS
     Problems
    1.45
     Relationship
    1.44
     Costs
    1.40
     Functions
    1.40
     Names
    1.38
     Values
    1.37
     Structure
    1.37
     Perspective
    1.37
     Issues
    1.35
     Function
    1.35
    Activations Density 0.433%

    No Known Activations