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. 3-RES-JB
    6. 21572
    Prev
    Next
    INDEX
    Explanations

    numerical values or specific phrases related to financial expenditures

    oai_token-act-pair · gpt-3.5-turbo

    terms related to financial outlays or spending

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Ryder
    -0.75
     Kirin
    -0.70
    ger
    -0.70
    Oracle
    -0.70
     Sie
    -0.65
    unin
    -0.64
     Marble
    -0.64
    Cola
    -0.61
     Keller
    -0.59
    olithic
    -0.59
    POSITIVE LOGITS
    itures
    1.24
     expenditure
    1.23
     expenditures
    1.10
     Expend
    1.02
     incurred
    0.98
    iture
    0.94
    ments
    0.85
     destro
    0.80
     Spending
    0.80
    ptions
    0.77
    Activations Density 0.008%

    No Known Activations