© 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. 4-RES-JB
    11. 14710
    Prev
    Next
    INDEX
    Explanations

    words related to international collaboration and partnerships

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "cooperation" in various contexts

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

    No Comments

    Negative Logits
    nova
    -0.75
    ibur
    -0.74
    thur
    -0.69
    ghazi
    -0.69
    gun
    -0.68
    apor
    -0.68
    ithe
    -0.67
    nos
    -0.67
    corn
    -0.66
    oak
    -0.65
    POSITIVE LOGITS
     cooperation
    0.95
     coordination
    0.89
    yip
    0.84
    DragonMagazine
    0.84
     agreement
    0.81
     cooperate
    0.79
     minded
    0.79
     efforts
    0.78
    operation
    0.76
     relationship
    0.75
    Activations Density 0.017%

    No Known Activations