© 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. 10-RES-JB
    11. 11148
    Prev
    Next
    INDEX
    Explanations

    terms related to principles or fundamental beliefs

    oai_token-act-pair · gpt-3.5-turbo

    references to foundational concepts or rules

    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
    IED
    -0.84
    noon
    -0.66
    minster
    -0.65
    sites
    -0.65
    tg
    -0.64
    Textures
    -0.63
    otte
    -0.63
    bor
    -0.63
    hiba
    -0.63
    ificant
    -0.63
    POSITIVE LOGITS
     principles
    1.09
     guiding
    1.03
     underpin
    1.01
     principle
    1.00
     governing
    0.98
    ciples
    0.94
     underlying
    0.93
     principals
    0.87
    ually
    0.86
     applied
    0.85
    Activations Density 0.058%

    No Known Activations