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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 22246
    Prev
    Next
    INDEX
    Explanations

    references to armed conflicts, weapons, and military-related terms

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "armed" in various contexts related to conflict or preparedness

    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
     Journals
    -0.72
    heim
    -0.72
     Sylv
    -0.70
     Growth
    -0.70
    rt
    -0.68
     Spa
    -0.66
    bum
    -0.66
    growth
    -0.65
    Hub
    -0.65
    Cube
    -0.64
    POSITIVE LOGITS
     armed
    3.73
     Armed
    2.40
    armed
    2.13
     arming
    1.92
     unarmed
    1.90
     armoured
    1.51
     armored
    1.48
     militia
    1.47
     milit
    1.45
    ilitary
    1.37
    Activations Density 0.015%

    No Known Activations