© 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 EvalsExportsAPI 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. 4-RES-JB
    11. 16803
    Prev
    Next
    INDEX
    Explanations

    terms related to social welfare programs

    oai_token-act-pair · gpt-3.5-turbo

    references to welfare

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

    No Comments

    Negative Logits
     Ou
    -0.70
    xual
    -0.68
    semble
    -0.66
     Sie
    -0.65
     Brun
    -0.64
    imb
    -0.63
     deaf
    -0.63
    ãģĻ
    -0.61
     mortar
    -0.60
    aque
    -0.59
    POSITIVE LOGITS
    elfare
    1.28
     welfare
    1.13
     Welfare
    0.96
    benefit
    0.94
     recipients
    0.91
     entitle
    0.91
     beneficiaries
    0.85
     reform
    0.83
    ega
    0.81
     Reform
    0.78
    Activations Density 0.011%

    No Known Activations