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

    Neuronpedia

    APISteerSAE EvalsBlog/PodcastNEWSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    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. 6795
    Prev
    Next
    INDEX
    Explanations

    mentions of people being linked or rumored in contexts such as roles, jobs or destinations

    oai_token-act-pair · gpt-3.5-turbo

    connections and links between individuals and organizations or teams

    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
    heit
    -0.80
    reflect
    -0.74
     Awareness
    -0.72
     Digest
    -0.71
    abiding
    -0.71
    burgh
    -0.70
    Statistics
    -0.69
    facts
    -0.69
    WARN
    -0.68
    govtrack
    -0.66
    POSITIVE LOGITS
     relocate
    0.95
     bids
    0.94
     possible
    0.87
     renegoti
    0.87
     involvement
    0.86
     bid
    0.86
     resurrect
    0.85
     loan
    0.84
     extradition
    0.84
     takeover
    0.82
    Activations Density 0.354%

    No Known Activations