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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 0-RES-JB
    11. 16401
    Prev
    Next
    INDEX
    Explanations

    references to poverty

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ingers
    -0.72
    CG
    -0.71
     Laser
    -0.71
    yz
    -0.71
     buds
    -0.68
    @@
    -0.67
     onboard
    -0.66
    wave
    -0.65
     Reply
    -0.63
     mL
    -0.63
    POSITIVE LOGITS
     poverty
    3.65
     Poverty
    2.74
    overty
    2.40
     homelessness
    1.82
     unemployment
    1.62
     impoverished
    1.61
     malnutrition
    1.56
     impover
    1.55
     poorest
    1.45
     famine
    1.45
    Activations Density 0.022%

    No Known Activations