© 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. 9-RES-JB
    11. 4914
    Prev
    Next
    INDEX
    Explanations

    references to the word "dollar"

    oai_token-act-pair · gpt-3.5-turbo

    references to currency, specifically the U.S. dollar

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ettings
    -0.75
    udic
    -0.70
     Fenrir
    -0.70
     Asgard
    -0.68
     Bast
    -0.68
    spective
    -0.67
    NetMessage
    -0.65
     Hav
    -0.65
    urus
    -0.64
     Surviv
    -0.62
    POSITIVE LOGITS
     sterling
    1.07
    dollar
    1.00
     dollar
    0.97
     hegemony
    0.94
     peg
    0.84
     currency
    0.84
     ($)
    0.82
     converter
    0.82
     pes
    0.82
     denomination
    0.81
    Activations Density 0.043%

    No Known Activations