© 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. 9-RES-JB
    11. 10221
    Prev
    Next
    INDEX
    Explanations

    terms related to social issues and societal disparities

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to systemic inequalities and access to essential services

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
     Trey
    -0.94
     Oath
    -0.89
     Devin
    -0.84
     Bigfoot
    -0.81
     Plaintiff
    -0.79
     Intercept
    -0.78
     Nunes
    -0.78
     âĸĪ
    -0.78
     Wiz
    -0.76
     Lovecraft
    -0.76
    POSITIVE LOGITS
     programmes
    1.25
     ageing
    1.19
     inequalities
    1.10
     OECD
    1.07
     poverty
    1.07
     NHS
    1.05
     behavioural
    1.00
     childcare
    0.99
     subsidies
    0.99
     policymakers
    0.99
    Activations Density 1.132%

    No Known Activations