Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 4605
    Prev
    Next
    INDEX
    Explanations

    terms related to professional gatherings or events

    oai_token-act-pair · gpt-3.5-turbo
    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
    MpServer
    -0.89
    shapeshifter
    -0.76
    inventoryQuantity
    -0.67
    soType
    -0.66
    SourceFile
    -0.66
    bats
    -0.65
    ãĤ¦ãĤ¹
    -0.65
    EMS
    -0.63
    Disclaimer
    -0.62
    ãĥ´ãĤ¡
    -0.62
    POSITIVE LOGITS
     collaborate
    1.09
     gather
    1.08
     behave
    1.06
     strive
    1.06
     communicate
    1.04
     compete
    1.02
     seek
    1.01
     rely
    0.99
     choose
    0.99
     assemble
    0.99
    Activations Density 0.296%

    No Known Activations