© 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. 2-RES-JB
    11. 9258
    Prev
    Next
    INDEX
    Explanations

    phrases related to large quantities of money or financial transactions

    oai_token-act-pair · gpt-3.5-turbo

    references to large sums of money, specifically in the trillions and billions range

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Sov
    -0.67
    grim
    -0.67
    aign
    -0.67
    Coun
    -0.67
    season
    -0.67
    Adv
    -0.66
    Baltimore
    -0.65
    sburgh
    -0.64
    Guard
    -0.63
    Recomm
    -0.62
    POSITIVE LOGITS
     billions
    1.05
     trillions
    0.91
    undo
    0.88
     dollars
    0.85
    ĸļ
    0.79
    ãĤ´ãĥ³
    0.78
    externalActionCode
    0.77
    osph
    0.77
    urance
    0.77
    umers
    0.76
    Activations Density 0.011%

    No Known Activations