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. 6734
    Prev
    Next
    INDEX
    Explanations

    phrases related to contrasting viewpoints or different sides of an argument

    oai_token-act-pair · gpt-3.5-turbo

    the presence of empty tokens or gaps in the text

    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
    quickShipAvailable
    -0.26
    inas
    -0.24
    inventoryQuantity
    -0.24
    csv
    -0.24
    anity
    -0.23
    rin
    -0.22
    wagen
    -0.22
    epad
    -0.22
     href
    -0.21
    =-=-
    -0.21
    POSITIVE LOGITS
     Azerb
    0.25
     embr
    0.24
     distingu
    0.23
     Tanz
    0.23
     Afgh
    0.22
     myster
    0.22
     millenn
    0.22
     Huss
    0.22
     hous
    0.21
     Zoro
    0.21
    Activations Density 7.690%

    No Known Activations