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. 16109
    Prev
    Next
    INDEX
    Explanations

    phrases related to the act of selling or purchase

    oai_token-act-pair · gpt-3.5-turbo

    terms related to the selling or marketing of books

    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
     Kira
    -0.60
     template
    -0.60
     Judicial
    -0.59
     pro
    -0.59
     background
    -0.59
     Azerbai
    -0.59
     responsive
    -0.59
     timeline
    -0.58
     proof
    -0.58
     Mandatory
    -0.58
    POSITIVE LOGITS
    sell
    4.64
    seller
    2.42
    selling
    2.33
     Sell
    1.73
    sold
    1.62
     sellers
    1.51
    buy
    1.45
     Selling
    1.43
     sell
    1.41
    sels
    1.40
    Activations Density 0.013%

    No Known Activations