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. 10-RES-JB
    6. 15790
    Prev
    Next
    INDEX
    Explanations

    phrases related to news and analysis on Israel, the Middle East, and the Jewish world

    oai_token-act-pair · gpt-3.5-turbo

    references to news and analysis related to current events, specifically from the frontlines of conflict areas

    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
    express
    -0.58
    itialized
    -0.55
     congr
    -0.53
     livest
    -0.52
    igslist
    -0.50
     »
    -0.48
    illon
    -0.48
    /#
    -0.47
    endum
    -0.47
     intern
    -0.47
    POSITIVE LOGITS
     Mechdragon
    0.75
    osion
    0.74
     certs
    0.69
    tnc
    0.64
    abad
    0.62
    oké
    0.62
    ushes
    0.61
     widest
    0.60
    ä¹
    0.56
    ombies
    0.56
    Activations Density 0.039%

    No Known Activations