© 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. 3-RES-JB
    6. 3235
    Prev
    Next
    INDEX
    Explanations

    terms related to military or political conflicts

    oai_token-act-pair · gpt-3.5-turbo

    words related to academic fields or concepts, particularly those involving the arts or social sciences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ĸļ
    -0.72
    jriwal
    -0.68
    abase
    -0.68
    ttle
    -0.67
     Hik
    -0.63
    pard
    -0.61
     fate
    -0.58
    orkshire
    -0.57
     Woods
    -0.57
     Disapp
    -0.57
    POSITIVE LOGITS
    monary
    0.90
    terson
    0.74
    aic
    0.73
    atche
    0.69
    itive
    0.67
    dating
    0.66
    rha
    0.64
    Thumbnail
    0.62
    ela
    0.61
    ople
    0.61
    Activations Density 0.264%

    No Known Activations