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. 0-RES-JB
    6. 9020
    Prev
    Next
    INDEX
    Explanations

    terms related to companionship or relationships with others

    oai_token-act-pair · gpt-3.5-turbo

    references to companions or companionship

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    hene
    -0.67
     Mills
    -0.66
    ulz
    -0.66
     Alexis
    -0.65
     Blocks
    -0.64
    zig
    -0.62
     hashes
    -0.62
    Blocks
    -0.62
    elt
    -0.61
    anks
    -0.61
    POSITIVE LOGITS
     companion
    3.95
     companions
    2.78
     Companion
    2.47
    Compan
    2.17
     Compan
    1.72
    compan
    1.60
     comrade
    1.29
     partner
    1.24
     colleague
    1.21
     buddy
    1.20
    Activations Density 0.013%

    No Known Activations