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. 9-RES-JB
    6. 415
    Prev
    Next
    INDEX
    Explanations

    information related to financial budgets and cuts

    oai_token-act-pair · gpt-3.5-turbo

    references to budget deficits and financial figures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    iquette
    -0.79
    heter
    -0.77
     voy
    -0.76
     stalk
    -0.75
     Mart
    -0.74
    authent
    -0.74
     boun
    -0.74
     passers
    -0.72
     testim
    -0.71
    redd
    -0.71
    POSITIVE LOGITS
     budget
    1.61
     deficit
    1.61
     budgetary
    1.55
     fiscal
    1.53
     appropriations
    1.50
     Fiscal
    1.48
    udget
    1.47
     Budget
    1.41
     budgets
    1.38
    budget
    1.37
    Activations Density 0.900%

    No Known Activations