© 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. 2-RES-JB
    11. 19540
    Prev
    Next
    INDEX
    Explanations

    financial terms related to expenses or spending

    oai_token-act-pair · gpt-3.5-turbo

    references to financial expenditures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Oracle
    -0.81
     Sie
    -0.76
     Ryder
    -0.69
    ger
    -0.67
    unin
    -0.65
    Cola
    -0.64
     Moj
    -0.63
     Marble
    -0.60
     Keller
    -0.60
    ker
    -0.60
    POSITIVE LOGITS
    itures
    1.33
     expenditure
    1.32
     expenditures
    1.17
     Expend
    1.07
    iture
    0.97
     incurred
    0.94
     budgets
    0.85
     Spending
    0.84
     allocations
    0.83
     shenan
    0.83
    Activations Density 0.010%

    No Known Activations