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

    Neuronpedia

    APISteerSAE EvalsBlog/PodcastNEWSlackPrivacy & 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. 8521
    Prev
    Next
    INDEX
    Explanations

    instances of the word "bon" with varying degrees of emphasis

    oai_token-act-pair · gpt-3.5-turbo

    references to "bond" or variations of it

    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
     Nightmares
    -0.67
     Å
    -0.64
    RPG
    -0.64
    antine
    -0.64
    Bear
    -0.63
    RAM
    -0.63
    GER
    -0.62
    MJ
    -0.61
    rama
    -0.61
    urred
    -0.61
    POSITIVE LOGITS
    NetMessage
    0.91
    nets
    0.88
    xual
    0.83
    ial
    0.83
    ioxide
    0.82
    oning
    0.78
    DragonMagazine
    0.77
     Rouge
    0.76
    omial
    0.76
     partName
    0.76
    Activations Density 0.051%

    No Known Activations