© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 10-RES-JB
    6. 911
    Prev
    Next
    INDEX
    Explanations

    mentions of individuals and their respective roles or titles in various organizations

    oai_token-act-pair · gpt-3.5-turbo

    prepositions and articles that indicate roles or positions related to directors and their organizations

    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
    usercontent
    -0.80
    Synopsis
    -0.76
     dstg
    -0.70
    Runner
    -0.69
     hereafter
    -0.68
    Example
    -0.65
    Previously
    -0.65
     desper
    -0.63
     lad
    -0.62
    fuck
    -0.62
    POSITIVE LOGITS
     communications
    1.04
     Programs
    0.94
     Operations
    0.93
     Strategic
    0.91
     Communications
    0.90
     operations
    0.89
     research
    0.85
    research
    0.85
     sociology
    0.83
     Marketing
    0.83
    Activations Density 0.077%

    No Known Activations