Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 10938
    Prev
    Next
    INDEX
    Explanations

    words related to animal breeding and reproduction

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of breeding

    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
    inness
    -1.06
    itsch
    -0.85
    ulhu
    -0.76
    uyomi
    -0.75
    alach
    -0.73
    uckles
    -0.73
    ica
    -0.72
    iere
    -0.71
    ictional
    -0.71
    asar
    -0.71
    POSITIVE LOGITS
     breeding
    1.25
     bred
    0.95
    GGGGGGGG
    0.81
     Frenzy
    0.77
    breeding
    0.77
     breed
    0.77
     nursery
    0.75
     organisms
    0.75
     Females
    0.73
     centers
    0.73
    Activations Density 0.022%

    No Known Activations