© 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. 10-RES-JB
    11. 11331
    Prev
    Next
    INDEX
    Explanations

    keywords related to official statements, official visits, and delegation activities

    oai_token-act-pair · gpt-3.5-turbo

    references to specific organizations or entities involved in operations or plans

    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
    Ohio
    -0.87
    Brexit
    -0.85
    California
    -0.81
    Romney
    -0.79
    Baltimore
    -0.77
    Indiana
    -0.77
    Seattle
    -0.76
    Boston
    -0.75
    Portland
    -0.75
    utterstock
    -0.74
    POSITIVE LOGITS
     Naj
    0.93
     Directorate
    0.93
     Azerb
    0.90
     the
    0.90
     KR
    0.90
     Polic
    0.87
     Yen
    0.86
     Ä
    0.86
     PK
    0.86
     Sector
    0.86
    Activations Density 0.570%

    No Known Activations