© 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. 6206
    Prev
    Next
    INDEX
    Explanations

    phrases related to helping people move out of poverty and back into the workforce

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to gaining employment and economic mobility

    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
    review
    -0.67
    ãĥ¼ãĥ³
    -0.64
    tes
    -0.64
     Ammo
    -0.63
    case
    -0.61
     Lavrov
    -0.61
    bye
    -0.60
    ec
    -0.59
    ãĥīãĥ©ãĤ´ãĥ³
    -0.58
     Beaut
    -0.58
    POSITIVE LOGITS
     poverty
    1.13
     shelters
    1.04
     professions
    1.02
     jobs
    0.99
     unemployment
    0.98
     employment
    0.96
     careers
    0.93
    overty
    0.90
     Poverty
    0.89
     households
    0.89
    Activations Density 0.249%

    No Known Activations