© 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. 11-RES-JB
    11. 22480
    Prev
    Next
    INDEX
    Explanations

    words related to policies and their impacts

    oai_token-act-pair · gpt-3.5-turbo

    keywords related to various forms of policy and governance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    assian
    -0.72
    sonian
    -0.70
    mite
    -0.66
    bart
    -0.65
     laugh
    -0.65
    utsche
    -0.65
     "$:/
    -0.64
    umo
    -0.62
    guyen
    -0.61
    iman
    -0.60
    POSITIVE LOGITS
     practices
    1.09
     patterns
    1.04
     trends
    1.01
     regimes
    1.00
     strategies
    0.98
     Practices
    0.95
    making
    0.93
    anship
    0.93
     Policies
    0.92
     policies
    0.91
    Activations Density 0.364%

    No Known Activations