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. 1-RES-JB
    6. 15176
    Prev
    Next
    INDEX
    Explanations

    terms related to currency, especially mentioning the US dollar

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the dollar and its value or status in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    */(
    -0.81
     Referred
    -0.75
     Lead
    -0.72
    est
    -0.70
     Radiation
    -0.70
    KEN
    -0.70
     Cosponsors
    -0.69
     Flavoring
    -0.68
    fitting
    -0.68
     Engineer
    -0.68
    POSITIVE LOGITS
     dollar
    1.31
    dollar
    1.16
     Dollar
    0.98
     dollars
    0.97
    ollar
    0.95
    hyde
    0.91
     sterling
    0.84
     ($)
    0.84
     fung
    0.81
     pes
    0.80
    Activations Density 0.010%

    No Known Activations