© 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. 12008
    Prev
    Next
    INDEX
    Explanations

    references to Russian entities or activities

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the Russians in relation to different 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
    utive
    -0.74
    ature
    -0.68
     protective
    -0.67
     promotional
    -0.67
     exclusive
    -0.66
     version
    -0.65
     sister
    -0.64
     gaming
    -0.63
     multi
    -0.63
    ciplinary
    -0.63
    POSITIVE LOGITS
     Russians
    2.38
     Germans
    2.36
     Iranians
    2.26
     Ukrainians
    2.25
     Egyptians
    2.21
     Iraqis
    2.20
     Italians
    2.18
     Greeks
    2.15
     Koreans
    2.07
     Poles
    2.06
    Activations Density 0.044%

    No Known Activations