© 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. 11-RES-JB
    11. 22513
    Prev
    Next
    INDEX
    Explanations

    words related to international collaborations or agreements, particularly involving the US

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "and" indicating connections or collaborations between entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    govtrack
    -0.77
    agnetic
    -0.63
     markup
    -0.62
    yout
    -0.62
    Sport
    -0.60
    ettings
    -0.59
    matter
    -0.59
     Surviv
    -0.59
    ubb
    -0.59
     nutrit
    -0.58
    POSITIVE LOGITS
     USSR
    1.18
     Europe
    1.12
     European
    1.06
     Europeans
    1.06
    Mexico
    1.02
     Canada
    0.97
     UK
    0.96
     Mexico
    0.96
     abroad
    0.96
     Israel
    0.95
    Activations Density 0.210%

    No Known Activations