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. 17162
    Prev
    Next
    INDEX
    Explanations

    words related to financial derivatives

    oai_token-act-pair · gpt-3.5-turbo

    terms related to financial derivatives

    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
    Poll
    -0.70
    Hun
    -0.69
     Hungry
    -0.68
    erv
    -0.66
     visits
    -0.63
     Alam
    -0.62
     Stub
    -0.60
    eman
    -0.60
     Owen
    -0.60
     Stevenson
    -0.60
    POSITIVE LOGITS
     derivatives
    4.02
     derivative
    3.56
     swaps
    1.42
     deriv
    1.41
     hybrids
    1.14
     equivalents
    1.11
     variants
    1.08
     derived
    1.07
    derived
    1.04
     sequels
    1.03
    Activations Density 0.032%

    No Known Activations