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. 11-RES-JB
    6. 15578
    Prev
    Next
    INDEX
    Explanations

    the words "this is the" followed by a single word or phrase

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "the."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    oros
    -0.81
    anches
    -0.77
    encers
    -0.77
    mares
    -0.74
    usters
    -0.74
    icates
    -0.73
    å§«
    -0.73
     enjoys
    -0.72
    vertisements
    -0.71
    axies
    -0.71
    POSITIVE LOGITS
     culmination
    1.09
     beginning
    1.06
     first
    1.03
     seventh
    1.00
     sixth
    1.00
     moment
    0.99
     fifth
    0.99
     fourth
    0.99
     longest
    0.97
     same
    0.97
    Activations Density 0.089%

    No Known Activations