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. 5745
    Prev
    Next
    INDEX
    Explanations

    phrases related to social connections and relationships

    oai_token-act-pair · gpt-3.5-turbo

    references to social connections or relationships

    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
     Gutenberg
    -0.74
    urgical
    -0.71
    ruction
    -0.69
    pex
    -0.66
    efficiency
    -0.66
     vacancy
    -0.66
     mandate
    -0.66
     Category
    -0.66
    urgy
    -0.65
    Analysis
    -0.64
    POSITIVE LOGITS
     friends
    3.37
    friends
    3.03
     buddies
    2.84
     pals
    2.77
     acquaintances
    2.67
    Friends
    2.44
     classmates
    2.35
     Friends
    2.24
     friendships
    2.22
     friend
    2.13
    Activations Density 0.033%

    No Known Activations