© 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. 11-RES-JB
    11. 1874
    Prev
    Next
    INDEX
    Explanations

    technical terms related to software updates, tools, and features

    oai_token-act-pair · gpt-3.5-turbo

    technical updates and features in software applications

    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
    qua
    -0.76
    piring
    -0.73
    amous
    -0.69
    bent
    -0.69
    dominated
    -0.65
    amy
    -0.63
    interstitial
    -0.63
    ngth
    -0.63
     Columb
    -0.62
    meaning
    -0.62
    POSITIVE LOGITS
     Plugin
    1.38
     SDK
    1.25
     plugin
    1.24
     Integration
    1.17
     detects
    1.16
    Plugin
    1.15
     addon
    1.11
     integration
    1.08
     Suite
    1.07
     Framework
    1.06
    Activations Density 0.256%

    No Known Activations