© 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. 10-RES-JB
    11. 21704
    Prev
    Next
    INDEX
    Explanations

    financial rewards or incentives mentioned in a text

    oai_token-act-pair · gpt-3.5-turbo

    monetary values and financial incentives

    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
    eworks
    -0.76
    eyed
    -0.73
    unci
    -0.70
    abama
    -0.69
    iths
    -0.69
    âĹ¼
    -0.67
    Sym
    -0.66
     trillions
    -0.65
    warts
    -0.65
    umerable
    -0.64
    POSITIVE LOGITS
    -$
    1.18
     increments
    1.12
     apiece
    1.03
     donation
    1.01
    /$
    1.00
     vouchers
    1.00
     Donation
    0.93
     voucher
    0.92
    USD
    0.92
     bonus
    0.91
    Activations Density 0.112%

    No Known Activations