© 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. 24159
    Prev
    Next
    INDEX
    Explanations

    currency in US dollars

    oai_token-act-pair · gpt-3.5-turbo

    mentions of currency amounts, specifically U.S. dollars

    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
    alities
    -0.74
    ppings
    -0.73
    borough
    -0.71
    zig
    -0.70
    laun
    -0.69
     Gutenberg
    -0.68
     Plymouth
    -0.68
    lication
    -0.66
     resemb
    -0.66
    quartered
    -0.65
    POSITIVE LOGITS
    USD
    1.11
     USD
    1.07
     ($)
    0.91
    ollar
    0.82
    MX
    0.76
    $
    0.73
    ICAN
    0.72
    Quantity
    0.72
    UAL
    0.71
    HL
    0.71
    Activations Density 0.007%

    No Known Activations