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

    Neuronpedia

    Jacobian LensNEW
    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. 8-RES-JB
    11. 22378
    Prev
    Next
    INDEX
    Explanations

    large sums of money

    oai_token-act-pair · gpt-3.5-turbo

    mentions of dollar amounts in the context of financial transactions or budgets

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Pend
    -0.77
     exerc
    -0.70
     Sidd
    -0.70
     Tid
    -0.70
     Noct
    -0.69
     Tatt
    -0.69
     Reborn
    -0.68
     Ital
    -0.67
     Dag
    -0.66
     Vid
    -0.65
    POSITIVE LOGITS
    $$
    1.16
    500
    1.04
    -$
    1.03
    150
    1.01
    200
    1.01
    100
    1.01
    300
    1.00
    250
    1.00
    400
    0.95
    350
    0.93
    Activations Density 0.063%

    No Known Activations