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. 7519
    Prev
    Next
    INDEX
    Explanations

    phrases related to political or economic topics, specifically discussing policies and regulations among member states

    oai_token-act-pair · gpt-3.5-turbo

    references to governance and member state regulations within the EU context

    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
    ãĥŁ
    -0.76
     Archdemon
    -0.76
    amaz
    -0.67
    nings
    -0.66
    phant
    -0.64
     pneumonia
    -0.63
    nesday
    -0.63
    apy
    -0.62
    MQ
    -0.62
     desper
    -0.61
    POSITIVE LOGITS
    overe
    0.72
    holder
    0.71
     Membership
    0.67
    holders
    0.63
    iris
    0.61
     Lauder
    0.59
    uties
    0.58
     holdings
    0.58
     delegated
    0.58
     Veteran
    0.58
    Activations Density 1.163%

    No Known Activations