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. 6-RES-JB
    6. 22188
    Prev
    Next
    INDEX
    Explanations

    mentions of the sourcing, exporting, importing, leasing, supplying, or renting of items

    oai_token-act-pair · gpt-3.5-turbo

    terms related to the trade and distribution of goods and resources

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    abet
    -0.81
    levels
    -0.80
    esa
    -0.75
    neg
    -0.74
    rek
    -0.72
    bra
    -0.72
    edom
    -0.72
    clerosis
    -0.72
    pan
    -0.71
    pad
    -0.71
    POSITIVE LOGITS
     extensively
    0.80
     copies
    0.77
    CLASSIFIED
    0.73
     notor
    0.70
     copyrighted
    0.68
    OUP
    0.67
     anonymously
    0.66
     millenn
    0.65
     Magnum
    0.64
     Hamm
    0.63
    Activations Density 0.131%

    No Known Activations