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. 2656
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "pun" and related forms in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    words related to puns

    oai_token-act-pair · gpt-3.5-turbo
    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
     Commons
    -0.75
     Empires
    -0.71
     Covenant
    -0.68
     Transparency
    -0.68
     Consent
    -0.66
    ORGE
    -0.65
     Preferred
    -0.64
     Journals
    -0.64
    éļ
    -0.62
     appointments
    -0.62
    POSITIVE LOGITS
    isher
    1.13
    ishers
    1.01
    pun
    1.00
    ting
    0.95
    cheon
    0.93
    ter
    0.93
    ball
    0.91
    ters
    0.91
    cher
    0.87
    oons
    0.85
    Activations Density 0.014%

    No Known Activations