© 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. 8-RES-JB
    11. 6922
    Prev
    Next
    INDEX
    Explanations

    phrases related to political events, especially concerning the United States

    oai_token-act-pair · gpt-3.5-turbo

    references to America's actions and positions in global conflicts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Samp
    -0.69
     upd
    -0.68
     pandemonium
    -0.66
     PCs
    -0.64
     Juven
    -0.62
     rumours
    -0.61
     presentations
    -0.61
     motions
    -0.60
     HF
    -0.59
     Alto
    -0.59
    POSITIVE LOGITS
     NATO
    0.96
     Nato
    0.94
     superpower
    0.90
    raltar
    0.90
    irst
    0.82
     abroad
    0.81
     overseas
    0.77
    illance
    0.76
     allies
    0.76
     unequ
    0.75
    Activations Density 0.579%

    No Known Activations