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. 7612
    Prev
    Next
    INDEX
    Explanations

    incidents related to deaths or injuries caused by various events

    oai_token-act-pair · gpt-3.5-turbo

    incidents or events that resulted in harm or fatalities

    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
    wcsstore
    -0.74
    atech
    -0.73
    ith
    -0.70
     nostalg
    -0.70
     behaves
    -0.69
    iths
    -0.67
    anwhile
    -0.66
    next
    -0.65
    dated
    -0.64
     indust
    -0.64
    POSITIVE LOGITS
     deaths
    1.25
     fatalities
    1.24
     amput
    1.16
     casualties
    1.09
     injuring
    1.08
     death
    1.05
     injuries
    1.04
     wounding
    1.01
     arrests
    0.97
     casualty
    0.91
    Activations Density 0.282%

    No Known Activations