© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 11-RES-JB
    11. 3327
    Prev
    Next
    INDEX
    Explanations

    socioeconomic issues related to poverty, lack of education, opportunity, joblessness, failing schools, inequalities, and corruption

    oai_token-act-pair · gpt-3.5-turbo

    terms related to social issues and systemic inequality

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    handle
    -0.77
    imei
    -0.74
    iple
    -0.73
    handler
    -0.72
     LEGO
    -0.72
     Therapy
    -0.72
    ODY
    -0.71
    Lago
    -0.71
     Collider
    -0.70
    poke
    -0.70
    POSITIVE LOGITS
     poverty
    1.51
     insecurity
    1.48
     inequality
    1.43
     instability
    1.42
     stagnation
    1.41
     unemployment
    1.37
     malnutrition
    1.33
     shortages
    1.32
     illiter
    1.31
     impover
    1.30
    Activations Density 0.281%

    No Known Activations