© 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. 15148
    Prev
    Next
    INDEX
    Explanations

    phrases related to global or national perspectives

    oai_token-act-pair · gpt-3.5-turbo

    terms related to different levels of geographic or political organization, focusing on international, national, and local contexts

    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
    anza
    -0.80
    LY
    -0.74
    eer
    -0.74
    ger
    -0.73
    nce
    -0.72
     Pirate
    -0.72
     Bengals
    -0.72
    ly
    -0.68
    pool
    -0.67
     Venice
    -0.67
    POSITIVE LOGITS
     speaking
    0.95
    available
    0.93
     minded
    0.92
     mandated
    0.92
     imposed
    0.91
    acceptable
    0.90
     sourced
    0.88
     insured
    0.87
     appropriated
    0.87
     priced
    0.86
    Activations Density 0.048%

    No Known Activations