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. 0-RES-JB
    6. 24509
    Prev
    Next
    INDEX
    Explanations

    instances where something is being purchased

    oai_token-act-pair · gpt-3.5-turbo

    references to the act of buying or acquiring items

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    adj
    -0.69
    ols
    -0.66
    otom
    -0.66
    ceans
    -0.64
    erb
    -0.63
     largeDownload
    -0.63
    GMT
    -0.62
    vati
    -0.62
    olated
    -0.61
    tics
    -0.60
    POSITIVE LOGITS
     purchase
    3.68
     Purchase
    2.56
     purchases
    2.53
     purchasing
    2.35
    Purchase
    2.34
     buy
    2.31
     purchased
    2.15
     sale
    2.06
    urchase
    1.93
     purchaser
    1.93
    Activations Density 0.013%

    No Known Activations