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. 14862
    Prev
    Next
    INDEX
    Explanations

    terms related to various types of trading, such as stock trading, options trading, and cryptocurrency trading

    oai_token-act-pair · gpt-3.5-turbo

    terms related to trading, particularly in financial and cryptocurrency contexts

    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
    ĺħ
    -0.91
    atever
    -0.81
    jac
    -0.80
    sis
    -0.71
    uture
    -0.69
    xus
    -0.68
    STD
    -0.68
    issance
    -0.68
    illy
    -0.67
    ĪĴ
    -0.65
    POSITIVE LOGITS
     trading
    0.93
    daq
    0.92
     ledger
    0.92
     traders
    0.91
     paperback
    0.82
     trader
    0.82
     Trading
    0.82
     futures
    0.80
     cards
    0.79
     synd
    0.78
    Activations Density 0.017%

    No Known Activations