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. 10-RES-JB
    6. 20175
    Prev
    Next
    INDEX
    Explanations

    keywords related to politics, economics, and society

    oai_token-act-pair · gpt-3.5-turbo

    phrases relating to societal and economic dynamics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    luaj
    -0.78
    BuyableInstoreAndOnline
    -0.74
    colour
    -0.74
     Trave
    -0.71
     Whilst
    -0.69
    20439
    -0.66
    igraph
    -0.66
    usalem
    -0.66
    ailand
    -0.65
    estyles
    -0.63
    POSITIVE LOGITS
     harms
    1.01
     anyway
    1.00
     coerc
    1.00
     incentiv
    0.98
     crappy
    0.97
     lousy
    0.96
     pesky
    0.90
     inefficient
    0.89
     contrace
    0.89
     inconven
    0.89
    Activations Density 0.895%

    No Known Activations