© 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. 11-RES-JB
    6. 6800
    Prev
    Next
    INDEX
    Explanations

    keywords related to laws, regulations, and bureaucratic processes

    oai_token-act-pair · gpt-3.5-turbo

    terms related to written works and bureaucratic processes

    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
    bart
    -0.97
    zee
    -0.86
    ofi
    -0.83
    ioxide
    -0.82
    erd
    -0.81
    lein
    -0.81
    heit
    -0.80
    lier
    -0.74
    dat
    -0.74
    awar
    -0.72
    POSITIVE LOGITS
     surrounds
    0.85
     pertaining
    0.84
     spanning
    0.81
     flows
    0.81
     loops
    0.81
     blends
    0.81
     spans
    0.80
     styles
    0.78
     depicting
    0.77
     surrounding
    0.77
    Activations Density 0.149%

    No Known Activations