© 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. 0-RES-JB
    6. 2499
    Prev
    Next
    INDEX
    Explanations

    phrases related to unleashing or causing explosive, impactful events

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "unleash" and references to volcanic activity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     alphabet
    -0.79
     passports
    -0.75
    Fair
    -0.73
    vest
    -0.73
    Recommend
    -0.73
     passport
    -0.68
    phan
    -0.68
    adian
    -0.67
     Bis
    -0.66
     identification
    -0.66
    POSITIVE LOGITS
     unleashed
    2.27
     unleash
    2.03
     unle
    1.96
     raging
    1.89
     erupt
    1.83
     volcano
    1.76
     eruption
    1.74
     spew
    1.62
     eru
    1.62
     raged
    1.61
    Activations Density 0.053%

    No Known Activations