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

    Neuronpedia

    APISteerSAE EvalsBlog/PodcastNEWSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 5-RES-JB
    6. 15162
    Prev
    Next
    INDEX
    Explanations

    values related to money and financial transactions

    oai_token-act-pair · gpt-3.5-turbo

    financial figures and statistics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    odox
    -0.78
    ossip
    -0.68
    heter
    -0.65
    bye
    -0.64
    ilyn
    -0.64
     dissenting
    -0.61
     hier
    -0.60
     throats
    -0.60
     benches
    -0.59
    xual
    -0.57
    POSITIVE LOGITS
     USD
    0.94
    USD
    0.94
     dollars
    0.89
    -$
    0.88
     Dollars
    0.81
    AUD
    0.80
     Bonds
    0.78
     annually
    0.78
     (£
    0.77
     reimburse
    0.77
    Activations Density 0.282%

    No Known Activations