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. 7-RES-JB
    6. 15079
    Prev
    Next
    INDEX
    Explanations

    instances where money is being spent

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "on" and its related phrases

    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
    soType
    -0.84
    SourceFile
    -0.83
    terness
    -0.82
    ONSORED
    -0.77
    ress
    -0.76
    externalActionCode
    -0.75
    llah
    -0.72
    DERR
    -0.71
    ItemThumbnailImage
    -0.71
    çͰ
    -0.70
    POSITIVE LOGITS
     behalf
    1.21
     frivol
    0.98
     upkeep
    0.93
     groceries
    0.92
     necessities
    0.84
     frivolous
    0.83
     extras
    0.82
     infrastructure
    0.82
     essentials
    0.81
     transportation
    0.81
    Activations Density 0.041%

    No Known Activations