© 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. 0-RES-JB
    11. 19866
    Prev
    Next
    INDEX
    Explanations

    mentions of the Kremlin

    oai_token-act-pair · gpt-3.5-turbo

    references to the Kremlin or its influence in political contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     bonded
    -0.82
    bee
    -0.70
    -->
    -0.68
     Ame
    -0.66
    AAA
    -0.66
     thru
    -0.65
    eph
    -0.62
    EH
    -0.61
    Fit
    -0.60
     Caleb
    -0.60
    POSITIVE LOGITS
     Kremlin
    3.80
    Moscow
    2.19
    Putin
    2.18
     Putin
    2.14
     Moscow
    2.10
     Russians
    1.94
    Russian
    1.94
     KGB
    1.93
     Russian
    1.90
    Russia
    1.75
    Activations Density 0.009%

    No Known Activations