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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 11-RES-JB
    6. 4273
    Prev
    Next
    INDEX
    Explanations

    words related to economic factors and financial inequality

    oai_token-act-pair · gpt-3.5-turbo

    concepts related to economic inequality and its implications

    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
     verbally
    -0.67
     unmarked
    -0.67
     honour
    -0.67
     mock
    -0.65
     Yose
    -0.65
     alias
    -0.65
     invitation
    -0.64
     Iro
    -0.64
     convers
    -0.63
     Honour
    -0.63
    POSITIVE LOGITS
     economies
    1.14
    Econom
    1.13
     Recession
    1.11
    wage
    1.11
     GDP
    1.08
     revenues
    1.07
     inflation
    1.06
     incomes
    1.06
     Econom
    1.06
    Population
    1.05
    Activations Density 0.641%

    No Known Activations