© 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
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 10-RES-JB
    11. 11563
    Prev
    Next
    INDEX
    Explanations

    mentions of financial fees

    oai_token-act-pair · gpt-3.5-turbo

    terms related to fees and charges

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    DonaldTrump
    -0.77
    ational
    -0.75
    ãĤ¨ãĥ«
    -0.70
    ullivan
    -0.70
    ocent
    -0.70
     Alma
    -0.69
    ulnerable
    -0.68
    arya
    -0.67
    ovie
    -0.67
    psc
    -0.66
    POSITIVE LOGITS
     levied
    1.24
     fees
    1.18
     waived
    1.14
     payable
    1.08
     waivers
    1.05
     incurred
    1.03
     reimbursement
    1.02
     fee
    1.01
     paid
    0.97
     waiver
    0.96
    Activations Density 0.031%

    No Known Activations