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. 15120
    Prev
    Next
    INDEX
    Explanations

    mentions of political summits and meetings

    oai_token-act-pair · gpt-3.5-turbo

    references to major international summits and their associated activities

    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
     Bucc
    -0.86
     Crow
    -0.81
     Vick
    -0.81
    ãĤ¨ãĥ«
    -0.79
     Rivera
    -0.77
    Gy
    -0.75
     Pru
    -0.73
     Trooper
    -0.73
     Avery
    -0.72
     Arpaio
    -0.72
    POSITIVE LOGITS
     summit
    1.50
     negotiators
    1.25
     Summit
    1.16
     convened
    1.16
     meeting
    1.14
     meetings
    1.14
    ilateral
    1.11
     treaty
    1.10
     Meeting
    1.09
     conference
    1.08
    Activations Density 0.291%

    No Known Activations