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. 23554
    Prev
    Next
    INDEX
    Explanations

    references to or mentions of physical money, specifically cash

    oai_token-act-pair · gpt-3.5-turbo

    references to cash or money transactions

    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
     Norn
    -0.74
     Breaker
    -0.73
    storms
    -0.72
     Destroyer
    -0.69
    iration
    -0.67
    sections
    -0.66
     ["
    -0.66
    yard
    -0.66
     Fract
    -0.65
    ãĢ
    -0.65
    POSITIVE LOGITS
     cash
    3.60
    cash
    2.58
    Cash
    2.45
     Cash
    2.43
     money
    1.87
     liquidity
    1.59
    money
    1.58
     Money
    1.51
    Money
    1.47
     dollars
    1.47
    Activations Density 0.019%

    No Known Activations