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. 4047
    Prev
    Next
    INDEX
    Explanations

    references to geopolitical relations between Russia and other countries or entities

    oai_token-act-pair · gpt-3.5-turbo

    references to Russian influence and involvement in various contexts

    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
     "$:/
    -0.77
     stub
    -0.73
    rake
    -0.65
     Dickinson
    -0.65
     Died
    -0.64
     jars
    -0.62
    isode
    -0.62
     antidote
    -0.60
    arers
    -0.60
     youngest
    -0.59
    POSITIVE LOGITS
    Äĩ
    0.95
    kaya
    0.94
    Äį
    0.86
    м
    0.85
     Serbia
    0.82
     Monteneg
    0.81
     Lavrov
    0.80
    achev
    0.80
    Sat
    0.78
    odan
    0.78
    Activations Density 0.342%

    No Known Activations