Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 11-RES-JB
    6. 4370
    Prev
    Next
    INDEX
    Explanations

    terms related to currency and financial markets

    oai_token-act-pair · gpt-3.5-turbo

    references to currency values and fluctuations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Campus
    -0.84
     Bucc
    -0.80
     Rath
    -0.72
     Illum
    -0.72
     Coh
    -0.71
     Coy
    -0.71
     Fenrir
    -0.70
     Scalia
    -0.70
     NCT
    -0.70
     Brennan
    -0.69
    POSITIVE LOGITS
     deval
    1.26
     depreciation
    1.17
     sterling
    1.16
     currencies
    1.12
     yen
    1.11
     deflation
    1.10
     yuan
    1.05
     peg
    1.03
    USD
    0.97
     currency
    0.96
    Activations Density 0.266%

    No Known Activations