© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 7-RES-JB
    11. 166
    Prev
    Next
    INDEX
    Explanations

    words related to international politics, specifically focusing on Russian and Turkish involvement

    oai_token-act-pair · gpt-3.5-turbo

    mentions of Russian entities or references in the context of international relations and military activities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    olkien
    -1.03
    byss
    -0.92
    utherford
    -0.85
    lished
    -0.85
    mble
    -0.84
    eus
    -0.81
    uckland
    -0.80
    odder
    -0.79
    igham
    -0.78
    regor
    -0.77
    POSITIVE LOGITS
     nationals
    1.19
     diplomats
    1.13
     embassies
    1.02
     government
    1.02
     citizens
    1.00
     authorities
    1.00
     nationalists
    0.99
     officials
    0.96
     nationalist
    0.95
     embassy
    0.94
    Activations Density 0.149%

    No Known Activations