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. 9-RES-JB
    6. 17058
    Prev
    Next
    INDEX
    Explanations

    terms related to democracy

    oai_token-act-pair · gpt-3.5-turbo

    references to democracy and democratic principles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    senal
    -0.88
    AMI
    -0.75
    thy
    -0.74
    ueless
    -0.73
    iple
    -0.72
    notes
    -0.72
    ifax
    -0.71
    hews
    -0.70
    abee
    -0.70
    Contact
    -0.70
    POSITIVE LOGITS
    ocracy
    0.82
    democracy
    0.81
     republic
    0.81
    ocrat
    0.81
     democracy
    0.81
     socialist
    0.76
     democracies
    0.75
     democratic
    0.75
     ideals
    0.74
     reform
    0.73
    Activations Density 0.051%

    No Known Activations