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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 5-RES-JB
    6. 16324
    Prev
    Next
    INDEX
    Explanations

    mentions of the term "Pirate" and related entities, like Pirate Bay and Pirate Party

    oai_token-act-pair · gpt-3.5-turbo

    references to "The Pirate Bay" and related terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    uggest
    -0.90
    enegger
    -0.81
    earchers
    -0.74
    cue
    -0.74
    olving
    -0.73
    ithing
    -0.73
    uating
    -0.71
    upon
    -0.70
    mble
    -0.69
    perse
    -0.69
    POSITIVE LOGITS
    Pir
    0.89
     Penguin
    0.87
     Pirate
    0.87
     Warrior
    0.84
     Party
    0.79
     Parties
    0.79
    Browser
    0.71
     Islands
    0.71
    lean
    0.71
     Caucus
    0.70
    Activations Density 0.015%

    No Known Activations