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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 11319
    Prev
    Next
    INDEX
    Explanations

    mentions of the country "Russia" or things related to Russia

    oai_token-act-pair · gpt-3.5-turbo

    references to Russia or Russian identity

    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
    -->
    -0.73
     :=
    -0.73
    arde
    -0.70
    CHR
    -0.67
    addle
    -0.67
     fmt
    -0.66
     Giles
    -0.66
    DH
    -0.65
     intrins
    -0.63
     [&
    -0.63
    POSITIVE LOGITS
     Russian
    3.58
    Russian
    3.19
     Russians
    2.96
     Kremlin
    2.60
     Russia
    2.59
    Russia
    2.55
     Ukrainian
    2.50
     Moscow
    2.40
    Moscow
    2.32
     Putin
    2.19
    Activations Density 0.015%

    No Known Activations