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. 7-RES-JB
    6. 18388
    Prev
    Next
    INDEX
    Explanations

    references to violent actions and conflicts involving casualties, particularly women and children

    oai_token-act-pair · gpt-3.5-turbo

    references to violence and its impact on civilians, particularly women and children

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Madison
    -0.84
    Scot
    -0.82
     Consumer
    -0.76
     Garfield
    -0.75
     Hamilton
    -0.75
     Cary
    -0.75
     Edison
    -0.74
    igmat
    -0.73
     Cullen
    -0.72
     Everett
    -0.72
    POSITIVE LOGITS
     Yemeni
    1.03
     Houth
    1.03
     Kazakh
    1.02
     Syrians
    0.97
    zbollah
    0.96
     Uzbek
    0.95
     Jihad
    0.95
     Yemen
    0.93
     PKK
    0.91
     smugglers
    0.90
    Activations Density 0.602%

    No Known Activations