© 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. 2-RES-JB
    6. 11876
    Prev
    Next
    INDEX
    Explanations

    words related to the concept of breeding, such as animals breeding, breeding programs, and breeding grounds

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "breeding" and related concepts

    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
    inness
    -1.03
    ulhu
    -0.82
    ournal
    -0.80
    alach
    -0.76
    ifest
    -0.76
    ifi
    -0.75
    hemy
    -0.74
    itsch
    -0.72
    ulz
    -0.71
    Downloadha
    -0.70
    POSITIVE LOGITS
     breeding
    1.27
     bred
    0.95
    breeding
    0.77
     organisms
    0.76
     breed
    0.75
     cages
    0.75
     tigers
    0.75
     Thumbnails
    0.74
     centers
    0.74
     Frenzy
    0.74
    Activations Density 0.015%

    No Known Activations