© 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
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 6-RES-JB
    11. 9796
    Prev
    Next
    INDEX
    Explanations

    references to wealth distribution, particularly related to taxing the rich and supporting the poor

    oai_token-act-pair · gpt-3.5-turbo

    terms related to wealth and class disparities, focusing on the rich and the poor

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Ô
    -0.93
    BuyableInstoreAndOnline
    -0.89
    agall
    -0.80
    tif
    -0.71
    utical
    -0.71
    phies
    -0.70
    ocol
    -0.70
     Izan
    -0.68
    pport
    -0.68
    ãĤ´ãĥ³
    -0.66
    POSITIVE LOGITS
    liest
    1.02
    est
    0.99
    ness
    0.77
    folk
    0.75
    hest
    0.74
    uce
    0.69
     ones
    0.68
     flock
    0.66
     portion
    0.66
     fared
    0.66
    Activations Density 0.143%

    No Known Activations