© 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. 1-RES-JB
    11. 14246
    Prev
    Next
    INDEX
    Explanations

    terms related to large business structures or organizations

    oai_token-act-pair · gpt-3.5-turbo

    terms related to corporate structures and economic power dynamics

    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
    etheless
    -0.83
     Presence
    -0.77
    erial
    -0.74
    lihood
    -0.72
    answered
    -0.71
     Symptoms
    -0.70
    OST
    -0.69
     Insp
    -0.67
     Asked
    -0.67
    bound
    -0.66
    POSITIVE LOGITS
     corporations
    1.06
     capitalists
    1.01
     conglomer
    1.00
     capitalism
    0.99
     capitalist
    0.97
     firms
    0.97
     conglomerate
    0.97
     monopol
    0.96
     corporation
    0.94
     unions
    0.93
    Activations Density 0.473%

    No Known Activations