© 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. 2-RES-JB
    11. 1625
    Prev
    Next
    INDEX
    Explanations

    words related to electricity or electrocution

    oai_token-act-pair · gpt-3.5-turbo

    words related to the concept of electricity or electric-related terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Twain
    -0.69
     Forth
    -0.64
     hope
    -0.63
     NASCAR
    -0.63
     HIP
    -0.62
     debtor
    -0.61
     specificity
    -0.59
     lack
    -0.59
     Seeking
    -0.58
    geist
    -0.58
    POSITIVE LOGITS
    kefeller
    1.40
    roc
    1.17
    oded
    1.00
    isco
    0.97
    ombat
    0.94
    ution
    0.94
    ody
    0.93
    ounter
    0.87
    rown
    0.87
    ultural
    0.85
    Activations Density 0.016%

    No Known Activations