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. 10968
    Prev
    Next
    INDEX
    Explanations

    financial terms

    oai_token-act-pair · gpt-3.5-turbo

    terms related to finance and economic themes

    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
     dried
    -0.80
     cherry
    -0.71
     samples
    -0.67
     heap
    -0.62
     drying
    -0.60
     dry
    -0.60
     Slav
    -0.60
     sample
    -0.59
     scar
    -0.59
     Wer
    -0.58
    POSITIVE LOGITS
    inance
    4.32
    inances
    2.30
     finance
    1.34
     Finance
    1.32
    inates
    1.09
    inant
    0.98
    enance
    0.95
    erity
    0.90
    ination
    0.90
    inate
    0.89
    Activations Density 0.015%

    No Known Activations