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. 23830
    Prev
    Next
    INDEX
    Explanations

    phrases related to collaboration and partnerships

    oai_token-act-pair · gpt-3.5-turbo

    the word "and" in various contexts, indicating a focus on conjunctions and connections between elements in the text

    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
    cms
    -0.76
    wcs
    -0.68
    =]
    -0.65
    places
    -0.65
    trop
    -0.62
    dayName
    -0.62
    ãĥİ
    -0.61
    Coming
    -0.60
    where
    -0.60
    Report
    -0.59
    POSITIVE LOGITS
     colleagues
    1.26
     others
    1.23
     fellow
    1.16
     his
    1.12
     colleague
    1.00
     coworkers
    0.99
     Associates
    0.99
     associates
    0.96
     collaborators
    0.91
     other
    0.91
    Activations Density 0.124%

    No Known Activations