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. 1-RES-JB
    6. 1553
    Prev
    Next
    INDEX
    Explanations

    mentions of the word "shrimp."

    oai_token-act-pair · gpt-3.5-turbo

    mentions of shrimp and related seafood products

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Pakistan
    -0.80
     Syd
    -0.77
    ب
    -0.76
    iah
    -0.72
    ãĤ¹ãĥĪ
    -0.70
    iop
    -0.69
     Sax
    -0.69
    Brand
    -0.68
     Radiant
    -0.67
    ENCE
    -0.66
    POSITIVE LOGITS
     shrimp
    1.30
     lobster
    1.09
     squid
    1.07
     crabs
    1.00
     crab
    0.99
    fish
    0.98
    rimp
    0.96
     shells
    0.92
     Squid
    0.90
     worms
    0.89
    Activations Density 0.011%

    No Known Activations