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. 20410
    Prev
    Next
    INDEX
    Explanations

    mentions of merchandise or items for sale

    oai_token-act-pair · gpt-3.5-turbo

    references to merchandise and related products

    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
    teen
    -0.76
    een
    -0.75
    FER
    -0.68
    lat
    -0.63
    EFF
    -0.62
    bern
    -0.62
    mond
    -0.62
    ths
    -0.61
     Pill
    -0.61
    oli
    -0.61
    POSITIVE LOGITS
    andise
    1.47
     merchandise
    1.29
     merch
    1.13
    wagon
    0.94
    abilia
    0.92
     apparel
    0.88
    leeve
    0.83
     Merch
    0.82
    afort
    0.80
    ocity
    0.78
    Activations Density 0.008%

    No Known Activations