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. 15880
    Prev
    Next
    INDEX
    Explanations

    phrases indicating a comparison or contrast between different concepts or situations

    oai_token-act-pair · gpt-3.5-turbo

    repetitive mentions of the phrase "at least."

    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
    FTWARE
    -0.77
    aceutical
    -0.71
    Fed
    -0.64
    alpha
    -0.63
    tools
    -0.62
    erness
    -0.61
    Pac
    -0.61
    OTUS
    -0.59
    itivity
    -0.58
    cro
    -0.58
    POSITIVE LOGITS
     least
    1.53
    onement
    1.13
    mosp
    0.98
    yp
    0.94
     times
    0.92
    ention
    0.89
    roph
    0.86
    hens
    0.85
    abase
    0.83
     variance
    0.81
    Activations Density 0.101%

    No Known Activations