Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 24377
    Prev
    Next
    INDEX
    Explanations

    notable person names or events

    oai_token-act-pair · gpt-3.5-turbo

    specific subjects of news articles or stories involving events and individuals

    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
     comple
    -0.77
     optimized
    -0.76
     transact
    -0.75
     enrich
    -0.75
    SPONSORED
    -0.72
     endeavor
    -0.72
     challeng
    -0.71
     expend
    -0.71
     redeem
    -0.70
     comprom
    -0.70
    POSITIVE LOGITS
     Former
    1.52
     Despite
    1.50
     Several
    1.42
     Hundreds
    1.41
     Thousands
    1.39
     Protesters
    1.39
     Following
    1.38
     Dozens
    1.38
     During
    1.37
     Another
    1.36
    Activations Density 0.138%

    No Known Activations