© 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. 4-RES-JB
    11. 7528
    Prev
    Next
    INDEX
    Explanations

    mentions of international activities, services, or connections

    oai_token-act-pair · gpt-3.5-turbo

    terms related to international contexts or activities

    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
    etsk
    -1.00
    veyard
    -0.92
    uden
    -0.86
    Downloadha
    -0.85
    bernatorial
    -0.85
    iffs
    -0.81
    thora
    -0.81
    addons
    -0.79
    aunders
    -0.78
    sbm
    -0.75
    POSITIVE LOGITS
     Affairs
    0.82
     affairs
    0.81
     Confederation
    0.73
     espionage
    0.73
     warming
    0.72
     acclaim
    0.71
     correspondent
    0.71
     postage
    0.71
     diplomatic
    0.71
     isolation
    0.69
    Activations Density 0.039%

    No Known Activations