© 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. 6-RES-JB
    11. 11750
    Prev
    Next
    INDEX
    Explanations

    keywords related to poverty

    oai_token-act-pair · gpt-3.5-turbo

    references to poverty

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    */(
    -0.81
    ERC
    -0.78
    ergy
    -0.78
    ership
    -0.75
    ateur
    -0.72
    ITNESS
    -0.72
    wcsstore
    -0.72
    natureconservancy
    -0.71
    ery
    -0.68
    azeera
    -0.67
    POSITIVE LOGITS
     allev
    1.14
     stricken
    0.95
     poverty
    0.88
    overty
    0.85
     wages
    0.81
     Poverty
    0.78
     wage
    0.76
     Wage
    0.74
     relief
    0.72
     erad
    0.72
    Activations Density 0.018%

    No Known Activations