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. 2-RES-JB
    6. 1089
    Prev
    Next
    INDEX
    Explanations

    references to large monetary amounts or financial transactions

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the term "dollars" in various contexts related to finance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    eworld
    -0.72
    sole
    -0.70
     Halls
    -0.68
    eor
    -0.67
    âĹ¼
    -0.66
    eways
    -0.65
    ezvous
    -0.65
    cknow
    -0.65
    Cover
    -0.64
    pmwiki
    -0.62
    POSITIVE LOGITS
     dollars
    1.22
     ($
    0.92
    $$
    0.90
     dollar
    0.89
    dollar
    0.87
     sterling
    0.83
     ($)
    0.81
     USD
    0.81
     worth
    0.79
    /$
    0.79
    Activations Density 0.021%

    No Known Activations