© 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. 10-RES-JB
    11. 16133
    Prev
    Next
    INDEX
    Explanations

    phrases related to economics and policies

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to social issues and community support

    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
     ðŁĻĤ
    -0.66
     (/
    -0.65
    :(
    -0.65
    Statement
    -0.60
    fuck
    -0.60
    Quote
    -0.60
     (#
    -0.59
    !!!
    -0.59
    Congratulations
    -0.58
     hereby
    -0.58
    POSITIVE LOGITS
     pricey
    0.76
     wealthier
    0.69
     pric
    0.66
     suburban
    0.66
     costly
    0.65
     tougher
    0.65
     ageing
    0.65
     ÂŃ
    0.62
     dwindling
    0.62
     nearby
    0.59
    Activations Density 1.255%

    No Known Activations