Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 7-RES-JB
    6. 611
    Prev
    Next
    INDEX
    Explanations

    large monetary figures typically in the context of finance or economics

    oai_token-act-pair · gpt-3.5-turbo

    references to large monetary amounts, especially in billions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    pring
    -0.69
    mons
    -0.68
    erness
    -0.66
    eve
    -0.66
    vil
    -0.65
     Coulter
    -0.64
    cers
    -0.63
    bable
    -0.61
    haps
    -0.61
    Crit
    -0.60
    POSITIVE LOGITS
     dollars
    1.10
    dollar
    0.95
     (£
    0.87
     USD
    0.86
     pounds
    0.85
     dollar
    0.83
     Dollars
    0.82
     annually
    0.82
    atform
    0.80
    -$
    0.78
    Activations Density 0.044%

    No Known Activations