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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 11-RES-JB
    6. 19920
    Prev
    Next
    INDEX
    Explanations

    mentions of welfare programs and benefits

    oai_token-act-pair · gpt-3.5-turbo

    terms related to welfare and assistance programs

    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
    semble
    -0.72
    ibel
    -0.70
    rays
    -0.70
    pert
    -0.68
    tumblr
    -0.67
    afort
    -0.66
    ulas
    -0.66
    canon
    -0.65
    lies
    -0.65
     Lego
    -0.65
    POSITIVE LOGITS
     recipients
    1.28
     beneficiaries
    1.15
     rolls
    1.03
     payments
    1.01
     eligibility
    0.97
     Benefits
    0.97
    elfare
    0.96
     reimbursement
    0.96
     programs
    0.95
     Administration
    0.94
    Activations Density 0.061%

    No Known Activations