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. 6-RES-JB
    6. 3128
    Prev
    Next
    INDEX
    Explanations

    phrases related to financial transactions and bank accounts

    oai_token-act-pair · gpt-3.5-turbo

    terms related to financial accounts and balances

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Zed
    -0.76
    Sund
    -0.69
    ï¸
    -0.65
    Spoiler
    -0.64
     clim
    -0.63
     Veh
    -0.62
     Galile
    -0.61
     Jury
    -0.61
    OVA
    -0.61
     goggles
    -0.61
    POSITIVE LOGITS
     payable
    1.07
     receipts
    1.04
     coffers
    0.99
     rece
    0.97
    ngth
    0.92
     creditor
    0.91
     amassed
    0.88
    flows
    0.87
     balances
    0.86
     creditors
    0.85
    Activations Density 0.092%

    No Known Activations