Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APISteerSAE EvalsBlog/PodcastNEWSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 5-RES-JB
    6. 16084
    Prev
    Next
    INDEX
    Explanations

    words related to social welfare assistance programs

    oai_token-act-pair · gpt-3.5-turbo

    references to social assistance and welfare programs

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Rum
    -0.78
    Temperature
    -0.78
    Sensor
    -0.75
     Cologne
    -0.74
    nit
    -0.71
    sbm
    -0.71
     Sie
    -0.71
    Ul
    -0.70
     sidx
    -0.70
     enthusi
    -0.66
    POSITIVE LOGITS
    elfare
    1.35
     beneficiaries
    1.14
     Medicaid
    1.14
     entitle
    1.05
     welfare
    1.05
     recipients
    1.03
     programs
    1.03
     Medicare
    1.03
     vouchers
    1.01
    amacare
    1.00
    Activations Density 0.133%

    No Known Activations