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. 8726
    Prev
    Next
    INDEX
    Explanations

    the word "Main" followed by a number, potentially related to different topics or entities

    oai_token-act-pair · gpt-3.5-turbo

    the term "Main" in various contexts within the text

    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
    IBLE
    -0.70
     firsthand
    -0.65
     relative
    -0.63
     Nieto
    -0.63
     aside
    -0.56
     bitters
    -0.56
    uracy
    -0.55
     elusive
    -0.55
     perfection
    -0.53
     lightly
    -0.53
    POSITIVE LOGITS
    tenance
    1.62
    stream
    1.38
    frame
    1.26
    street
    1.19
    deck
    1.14
    stay
    1.12
    yu
    1.10
    lining
    1.08
    lander
    1.03
    ichi
    1.01
    Activations Density 0.024%

    No Known Activations