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. 0-RES-JB
    6. 14120
    Prev
    Next
    INDEX
    Explanations

    phrases related to exchange-traded funds (ETFs) with a particular focus on TF 9

    oai_token-act-pair · gpt-3.5-turbo

    abbreviations and terms related to financial instruments, specifically Exchange-Traded Funds (ETFs)

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     bell
    -0.74
     Greenwood
    -0.71
     Collins
    -0.70
     Mov
    -0.67
     Marion
    -0.66
     Ved
    -0.65
    idon
    -0.64
     Edison
    -0.64
     Louisiana
    -0.64
     Len
    -0.64
    POSITIVE LOGITS
    TF
    4.38
    tf
    2.35
     TF
    2.00
    ETF
    1.54
    TP
    1.52
    TG
    1.44
     tf
    1.41
    TC
    1.34
    DF
    1.32
    TS
    1.32
    Activations Density 0.010%

    No Known Activations