© 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. 11224
    Prev
    Next
    INDEX
    Explanations

    mentions of living things or concepts related to living entities

    oai_token-act-pair · gpt-3.5-turbo

    variations of the word "living."

    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
    EStream
    -1.00
    elight
    -0.87
    igham
    -0.81
    osen
    -0.81
    reg
    -0.81
    uyomi
    -0.79
    sonian
    -0.73
    aminer
    -0.72
    atility
    -0.72
    gomery
    -0.72
    POSITIVE LOGITS
     Wage
    1.10
    lihood
    0.89
     wage
    0.87
     Living
    0.85
     liv
    0.85
    living
    0.85
     quarters
    0.84
    Living
    0.82
    hart
    0.80
     living
    0.76
    Activations Density 0.020%

    No Known Activations