© 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. 1-RES-JB
    11. 5493
    Prev
    Next
    INDEX
    Explanations

    organizations, initiatives, or movements related to social or political advocacy

    oai_token-act-pair · gpt-3.5-turbo

    mentions of organizations and advocacy groups related to social and political issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    flows
    -0.77
     Zheng
    -0.72
    adal
    -0.72
     checkout
    -0.67
     Liang
    -0.66
     yog
    -0.64
     landfall
    -0.63
     è
    -0.62
    Äĩ
    -0.62
     prelim
    -0.62
    POSITIVE LOGITS
     Society
    1.03
     Fund
    0.92
     Against
    0.92
     Poverty
    0.91
     Matters
    0.88
     Equality
    0.88
     Institute
    0.88
     Monitoring
    0.87
     Network
    0.85
     Initiative
    0.84
    Activations Density 0.150%

    No Known Activations