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. 21160
    Prev
    Next
    INDEX
    Explanations

    mentions of summits or negotiation tables in a political context

    oai_token-act-pair · gpt-3.5-turbo

    references to peace negotiations and diplomacy

    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
     Rivera
    -0.78
     Randy
    -0.73
     mills
    -0.71
     Ralph
    -0.70
     Gawker
    -0.68
    Sensor
    -0.68
     pim
    -0.68
     Levi
    -0.67
     Eaton
    -0.67
     Walton
    -0.66
    POSITIVE LOGITS
     Nato
    1.25
     diplomatic
    1.23
    plom
    1.23
    ilateral
    1.21
     bilateral
    1.09
     diplomacy
    1.08
     Jinping
    1.07
     envoy
    1.07
     ceasefire
    1.06
     Lavrov
    1.06
    Activations Density 0.575%

    No Known Activations