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. 11-RES-JB
    6. 16990
    Prev
    Next
    INDEX
    Explanations

    phrases related to fishing operations and related activities

    oai_token-act-pair · gpt-3.5-turbo

    details about fishing operations and their regulations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    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
     Mandela
    -1.01
    Tesla
    -0.87
    nexus
    -0.85
     Chandra
    -0.85
     apartheid
    -0.83
     Villa
    -0.82
    Chicago
    -0.82
     Mubarak
    -0.81
     iCloud
    -0.79
    sbm
    -0.79
    POSITIVE LOGITS
     fish
    2.25
     salmon
    2.15
     fishes
    2.13
     trout
    2.12
    Fish
    1.98
     fisher
    1.96
     fishing
    1.90
    fish
    1.89
     fisherman
    1.85
     fishermen
    1.85
    Activations Density 0.241%

    No Known Activations