© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    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. 15548
    Prev
    Next
    INDEX
    Explanations

    phrases related to financial transactions and fees

    oai_token-act-pair · gpt-3.5-turbo

    mentions of various types of fees associated with services or transactions

    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
    DonaldTrump
    -0.76
     Alma
    -0.75
    ãĤ¨ãĥ«
    -0.75
    ocent
    -0.75
    psc
    -0.72
    ational
    -0.72
    ovie
    -0.69
    ullivan
    -0.67
    arya
    -0.66
     Alive
    -0.64
    POSITIVE LOGITS
     levied
    1.18
     fees
    1.12
     waived
    1.06
     waivers
    1.05
     incurred
    1.00
     payable
    0.97
     reimbursement
    0.97
     waiver
    0.95
     fee
    0.93
     imposed
    0.91
    Activations Density 0.049%

    No Known Activations