© 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. 4-RES-JB
    6. 19653
    Prev
    Next
    INDEX
    Explanations

    phrases related to being unstoppable or irreplaceable

    oai_token-act-pair · gpt-3.5-turbo

    forms of the word "able" indicating capability or potential

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

    No Comments

    Negative Logits
    erva
    -0.93
    udeb
    -0.87
    icion
    -0.86
    aeper
    -0.83
    itect
    -0.83
    ffield
    -0.79
    alyst
    -0.78
    atered
    -0.76
    avers
    -0.75
    icka
    -0.74
    POSITIVE LOGITS
     Haram
    0.84
     Danger
    0.78
     Islands
    0.73
    âĶĢâĶĢ
    0.71
    adoes
    0.70
     Zip
    0.69
     Isles
    0.67
     flaw
    0.66
     Skies
    0.66
    nesses
    0.64
    Activations Density 0.041%

    No Known Activations