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. 9046
    Prev
    Next
    INDEX
    Explanations

    words related to political conflicts and international relations, particularly involving countries like Syria, Iraq, Iran, and military actions

    oai_token-act-pair · gpt-3.5-turbo

    mentions of conflicts and geopolitical issues involving specific 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
    ATA
    -0.75
     Quadro
    -0.75
    tumblr
    -0.73
    åĭ
    -0.73
    erenn
    -0.67
    earable
    -0.67
    )=(
    -0.66
    document
    -0.65
    raw
    -0.64
    cms
    -0.63
    POSITIVE LOGITS
     uranium
    0.85
    ghazi
    0.82
     nuclear
    0.80
    abad
    0.75
     missile
    0.73
     plutonium
    0.71
     hoax
    0.71
     bombing
    0.71
     threats
    0.70
     proliferation
    0.68
    Activations Density 0.165%

    No Known Activations