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. 10-RES-JB
    6. 24227
    Prev
    Next
    INDEX
    Explanations

    words related to importance or emphasis

    oai_token-act-pair · gpt-3.5-turbo

    the presence of the word "be" in various forms and contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     hoops
    -0.69
     Blocks
    -0.61
     Sr
    -0.60
     accommodation
    -0.60
     Kurd
    -0.59
     Kamp
    -0.59
     Orbit
    -0.58
     orbit
    -0.58
     impossibility
    -0.58
     hops
    -0.58
    POSITIVE LOGITS
    hemoth
    1.47
    arers
    1.42
    fitting
    1.34
    ardless
    1.32
    heading
    1.31
    ige
    1.31
    league
    1.29
    acons
    1.28
    eping
    1.23
    agle
    1.23
    Activations Density 0.034%

    No Known Activations