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. 2-RES-JB
    6. 8602
    Prev
    Next
    INDEX
    Explanations

    references to purchasing something or looking for something that can be bought in various contexts

    oai_token-act-pair · gpt-3.5-turbo

    the word "purchase" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    erella
    -0.74
    inas
    -0.74
    sle
    -0.70
    hov
    -0.70
    amer
    -0.68
    opez
    -0.65
    assin
    -0.65
    uum
    -0.64
     Nas
    -0.64
    bered
    -0.64
    POSITIVE LOGITS
     purchases
    1.14
    iture
    1.06
    itures
    1.01
    Purchase
    1.00
     purchase
    0.99
     purchasing
    0.97
     buys
    0.89
    ment
    0.87
     buying
    0.84
     purchased
    0.82
    Activations Density 0.023%

    No Known Activations