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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 7971
    Prev
    Next
    INDEX
    Explanations

    terms related to governmental agencies, particularly the Environmental Protection Agency

    oai_token-act-pair · gpt-3.5-turbo

    references to government agencies and their roles in environmental and financial protection

    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
    flows
    -0.72
    Äĩ
    -0.69
    worthy
    -0.65
    yang
    -0.62
     balloons
    -0.61
    rose
    -0.60
    hower
    -0.59
    worms
    -0.58
    clone
    -0.57
    jin
    -0.57
    POSITIVE LOGITS
     Agency
    1.02
     Board
    1.01
     Association
    0.98
     Regulatory
    0.97
     Authority
    0.97
     Administration
    0.96
     Bureau
    0.93
     Act
    0.90
     Commission
    0.90
     Institute
    0.88
    Activations Density 0.113%

    No Known Activations