© 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. 10-RES-JB
    11. 17520
    Prev
    Next
    INDEX
    Explanations

    references to military-related terms, such as specific country names, military ranks, and weapons

    oai_token-act-pair · gpt-3.5-turbo

    references to grenades and related military terms

    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
    stakes
    -0.79
    orporated
    -0.71
    terson
    -0.69
    cript
    -0.68
    Penn
    -0.67
    tale
    -0.67
    gres
    -0.67
    tle
    -0.64
    elf
    -0.64
    enance
    -0.63
    POSITIVE LOGITS
    adier
    0.98
     Launcher
    0.76
     Grenade
    0.75
     grenades
    0.74
    adian
    0.72
     grenade
    0.72
    vernment
    0.69
     launchers
    0.66
    oses
    0.65
    inches
    0.64
    Activations Density 0.081%

    No Known Activations