© 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. 24034
    Prev
    Next
    INDEX
    Explanations

    technical or programming-related terms and code snippets

    oai_token-act-pair · gpt-3.5-turbo

    technical terms related to programming and memory management

    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
     enthusi
    -0.66
    edin
    -0.63
     catering
    -0.63
     burgeoning
    -0.61
     sorely
    -0.60
     Cassidy
    -0.60
     sadly
    -0.59
     Brent
    -0.59
    prising
    -0.59
    iola
    -0.58
    POSITIVE LOGITS
     integer
    1.02
     parentheses
    0.99
     modifier
    0.99
     comma
    0.99
     noun
    0.98
     integers
    0.96
     verb
    0.96
     boolean
    0.92
     vertex
    0.92
     modifiers
    0.92
    Activations Density 0.808%

    No Known Activations