© 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 EvalsExportsinterp-engineNEWAPI 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. 11-RES-JB
    11. 11501
    Prev
    Next
    INDEX
    Explanations

    financial and welfare-related terms and benefits such as tax credits, insurance plans, and social security programs

    oai_token-act-pair · gpt-3.5-turbo

    terms related to government assistance programs and social welfare

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     harbour
    -0.70
    GMT
    -0.68
    stanbul
    -0.68
    isy
    -0.67
    Gamer
    -0.66
     Wand
    -0.66
    jee
    -0.64
     arte
    -0.64
    esthetic
    -0.63
     Alb
    -0.63
    POSITIVE LOGITS
     eligibility
    1.14
     premiums
    1.11
     entitle
    1.06
    amacare
    1.06
     entitlement
    1.03
     rebate
    1.01
     benefits
    1.01
     repayment
    1.00
     Disability
    1.00
     reimburse
    0.99
    Activations Density 0.219%

    No Known Activations