© 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. 13363
    Prev
    Next
    INDEX
    Explanations

    phrases related to financial struggles or economic challenges

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to socioeconomic struggles and challenges

    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
     Appearance
    -0.70
    obbies
    -0.69
    perture
    -0.68
    irmation
    -0.67
     Pos
    -0.66
    ournals
    -0.65
     Subtle
    -0.64
     Clar
    -0.64
    imental
    -0.63
     Samurai
    -0.63
    POSITIVE LOGITS
     poorer
    1.19
     deprived
    1.16
     inconven
    1.13
     disadvantaged
    1.10
     uninsured
    1.10
     displaced
    1.09
     adversely
    1.08
     harmed
    1.06
     footing
    1.05
     disenfranch
    1.04
    Activations Density 0.196%

    No Known Activations