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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 9-RES-JB
    6. 20827
    Prev
    Next
    INDEX
    Explanations

    mentions of cutting or reducing something, such as costs, taxes, or regulations

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of reducing or eliminating something, particularly through the use of the word "cut."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Monitor
    -0.66
    DonaldTrump
    -0.65
     Organisation
    -0.62
     Moder
    -0.62
    perse
    -0.62
    sit
    -0.61
    btn
    -0.61
     Gutenberg
    -0.61
     Remastered
    -0.61
    Newsletter
    -0.60
    POSITIVE LOGITS
    thro
    1.17
    scenes
    1.12
    lasses
    1.08
    scene
    1.06
     ties
    1.01
    backs
    0.99
    aneous
    0.96
    tle
    0.92
     bait
    0.91
     corners
    0.91
    Activations Density 0.046%

    No Known Activations