© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 12-RES-JB
    11. 2511
    Prev
    Next
    INDEX
    Explanations

    terms related to socio-political and economic issues, particularly focusing on inequalities and dependencies

    oai_token-act-pair · gpt-3.5-turbo
    Triggered by @bot

    terms related to socio-economic and political issues

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 12-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.hook_resid_post
    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_post
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
     reel
    -0.69
     Guinness
    -0.68
     passage
    -0.67
     strips
    -0.65
     Shine
    -0.64
     discarded
    -0.63
     Forth
    -0.61
     terminated
    -0.61
     recipients
    -0.61
     breath
    -0.61
    POSITIVE LOGITS
    economic
    1.59
    political
    1.57
    technical
    1.43
    econom
    1.33
    cultural
    1.32
    environment
    1.31
    engineering
    1.28
    politics
    1.27
    ethical
    1.27
    financial
    1.26
    Activations Density 0.103%

    No Known Activations