© 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. 10699
    Prev
    Next
    INDEX
    Explanations

    words related to social, political, economic, and governance issues

    oai_token-act-pair · gpt-3.5-turbo

    terms related to social, political, and economic issues or influences

    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
     oranges
    -0.86
    cakes
    -0.79
    eers
    -0.78
     Decay
    -0.74
     Hera
    -0.74
     Shadows
    -0.72
    obos
    -0.71
    swick
    -0.71
    loads
    -0.71
    ombies
    -0.70
    POSITIVE LOGITS
     linguistic
    1.32
     psychological
    1.31
     philosophical
    1.28
     physiological
    1.28
     cultural
    1.26
     economical
    1.24
     behavioral
    1.23
     ideological
    1.22
     societal
    1.22
     logistical
    1.21
    Activations Density 0.177%

    No Known Activations