Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 10-RES-JB
    6. 15920
    Prev
    Next
    INDEX
    Explanations

    keywords related to the Soviet Union and communism

    oai_token-act-pair · gpt-3.5-turbo

    references to the Soviet Union and its associated aspects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    butt
    -0.82
    enance
    -0.79
    shots
    -0.72
     Huff
    -0.72
    epad
    -0.71
    gered
    -0.70
    hire
    -0.69
    ño
    -0.68
    ascar
    -0.68
    Thom
    -0.67
    POSITIVE LOGITS
     Union
    1.35
     KGB
    0.97
     dictator
    0.97
     bloc
    0.97
     USSR
    0.96
     Soviet
    0.89
    oslov
    0.86
     communism
    0.85
     era
    0.85
     Communism
    0.84
    Activations Density 0.044%

    No Known Activations