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

    Neuronpedia

    APISteerSAE EvalsBlog/PodcastNEWSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 5-RES-JB
    6. 18086
    Prev
    Next
    INDEX
    Explanations

    mentions of large quantities of money

    oai_token-act-pair · gpt-3.5-turbo

    phrases referencing large quantities of people or amounts of money

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    imen
    -0.81
    mentioned
    -0.69
    Adv
    -0.67
    cial
    -0.67
    ãĥ¤
    -0.62
    iban
    -0.62
    Condition
    -0.61
    anooga
    -0.61
    occup
    -0.59
    tein
    -0.59
    POSITIVE LOGITS
    aires
    0.99
    aire
    0.94
     dollars
    0.92
     billions
    0.83
     euros
    0.81
     litres
    0.79
     Millions
    0.79
    ujah
    0.78
     ILCS
    0.78
     millions
    0.77
    Activations Density 0.027%

    No Known Activations