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

    Neuronpedia

    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. 10-RES-JB
    11. 6319
    Prev
    Next
    INDEX
    Explanations

    terms related to government assistance programs like welfare, Medicaid, food stamps, and benefits

    oai_token-act-pair · gpt-3.5-turbo

    terms related to welfare programs and benefits

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Gamer
    -0.79
    Ô
    -0.74
    £ı
    -0.74
    Sensor
    -0.71
     mosqu
    -0.71
    Ul
    -0.70
    natureconservancy
    -0.68
     Alb
    -0.67
    ãĤ¶
    -0.67
    ãĤ¨ãĥ«
    -0.67
    POSITIVE LOGITS
     entitle
    1.34
     eligibility
    1.23
     payments
    1.22
     recipients
    1.21
     reimburse
    1.21
     entitlement
    1.16
     allowance
    1.16
     Disability
    1.15
     repayment
    1.14
     payable
    1.13
    Activations Density 0.175%

    No Known Activations