© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 0-RES-JB
    11. 5296
    Prev
    Next
    INDEX
    Explanations

    mentions of casualties or similar terms related to injury or harm

    oai_token-act-pair · gpt-3.5-turbo

    mentions of casualties and fatalities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    lip
    -0.74
    ibe
    -0.72
    creen
    -0.69
    pe
    -0.68
    ribe
    -0.68
     Smooth
    -0.68
    arter
    -0.66
    hered
    -0.66
    UE
    -0.65
    oku
    -0.64
    POSITIVE LOGITS
     casualties
    3.62
     casualty
    2.66
     fatalities
    2.06
     deaths
    1.66
     injuries
    1.44
     losses
    1.42
     Deaths
    1.41
     bloodshed
    1.40
     hostages
    1.34
     carnage
    1.30
    Activations Density 0.015%

    No Known Activations