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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 0-RES-JB
    6. 5560
    Prev
    Next
    INDEX
    Explanations

    mentions of "VA" (Veterans Affairs) and associated terms

    oai_token-act-pair · gpt-3.5-turbo

    references to the Veterans Affairs (VA) organization

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Cycl
    -0.69
    asketball
    -0.67
     rings
    -0.65
    ideshow
    -0.64
     clutch
    -0.64
     Bruno
    -0.63
    â
    -0.63
     mathemat
    -0.61
    iment
    -0.60
    onym
    -0.60
    POSITIVE LOGITS
     VA
    3.94
    VA
    2.15
     Va
    1.72
     Veterans
    1.72
     Virginia
    1.56
    Virginia
    1.43
     VT
    1.40
     DOD
    1.40
     GA
    1.38
     TN
    1.35
    Activations Density 0.009%

    No Known Activations