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. 12-RES-JB
    6. 14610
    Prev
    Next
    INDEX
    Explanations

    phrases related to wildlife and nature reserves

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot

    terms related to wildlife conservation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 12-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.hook_resid_post
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Beats
    -0.72
     Yamato
    -0.66
    mus
    -0.66
     Osc
    -0.65
    abi
    -0.64
    Machine
    -0.64
     Alibaba
    -0.64
    phabet
    -0.63
    utations
    -0.63
    ento
    -0.61
    POSITIVE LOGITS
     Refuge
    1.21
     refuge
    1.14
     biologists
    1.00
     biologist
    1.00
     rehabilit
    0.99
     sanctuary
    0.99
     Sanctuary
    0.99
     habitat
    0.95
     keeper
    0.90
     Conservation
    0.90
    Activations Density 0.088%

    No Known Activations