© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 2-RES-JB
    6. 23506
    Prev
    Next
    INDEX
    Explanations

    terms related to wealth and financial concepts

    oai_token-act-pair · gpt-3.5-turbo

    references to wealth and financial concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Interstitial
    -0.88
    ROR
    -0.81
    ãģ¦
    -0.77
    Earth
    -0.68
    apple
    -0.68
    1966
    -0.66
    ATIONS
    -0.66
    cause
    -0.65
     Defenders
    -0.64
    cers
    -0.64
    POSITIVE LOGITS
     wealth
    1.11
     inequality
    1.01
    ocracy
    0.93
     disparity
    0.90
     earners
    0.89
    ocrats
    0.88
     holdings
    0.87
     redistribution
    0.87
     disparities
    0.87
     accumulation
    0.86
    Activations Density 0.008%

    No Known Activations