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. 8-RES-JB
    6. 5368
    Prev
    Next
    INDEX
    Explanations

    countries and regions in comparison to Western countries in terms of safety or standards

    oai_token-act-pair · gpt-3.5-turbo

    references to Western countries and their influence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    staking
    -0.85
    govtrack
    -0.74
    asma
    -0.73
    iatrics
    -0.70
    Æ
    -0.69
    uracy
    -0.68
    pell
    -0.67
    chery
    -0.67
    hod
    -0.67
    ossession
    -0.67
    POSITIVE LOGITS
     Hemisphere
    1.22
     Sahara
    0.99
     Union
    0.93
    ization
    0.91
     hemisphere
    0.91
     democracies
    0.88
     Civilization
    0.88
     Balkans
    0.87
    isation
    0.86
     countries
    0.86
    Activations Density 0.032%

    No Known Activations