Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 7-RES-JB
    6. 12628
    Prev
    Next
    INDEX
    Explanations

    phrases related to political and social commentary

    oai_token-act-pair · gpt-3.5-turbo

    references to power structures and control by elites

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Finder
    -0.68
    gallery
    -0.67
    arij
    -0.63
    oother
    -0.61
    okingly
    -0.61
     aback
    -0.61
    undrum
    -0.60
     Oaks
    -0.59
     Guinness
    -0.57
     âĢº
    -0.57
    POSITIVE LOGITS
     neoliberal
    0.90
     totalitarian
    0.89
     tyranny
    0.88
     imperialist
    0.88
     Democr
    0.86
     unchecked
    0.86
     scapego
    0.86
     hegemony
    0.84
    ocrats
    0.83
     militar
    0.83
    Activations Density 1.599%

    No Known Activations