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. 23124
    Prev
    Next
    INDEX
    Explanations

    information related to countries and their rankings or actions

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to international relations and actions taken by countries

    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
    personal
    -0.77
     presentations
    -0.69
    asonable
    -0.66
    lihood
    -0.65
    Reilly
    -0.64
    eah
    -0.62
    evin
    -0.61
     motivational
    -0.61
    Sense
    -0.61
    otions
    -0.61
    POSITIVE LOGITS
     Nato
    0.93
     NATO
    0.83
     GDP
    0.82
     abroad
    0.82
     annexed
    0.81
     sovereign
    0.81
    ahime
    0.80
     WTO
    0.79
     economically
    0.79
     borders
    0.79
    Activations Density 0.919%

    No Known Activations