© 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. 20422
    Prev
    Next
    INDEX
    Explanations

    mentions of civilians involved in various situations or conflicts

    oai_token-act-pair · gpt-3.5-turbo

    references to civilians in conflict situations

    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
    chip
    -0.76
     Hole
    -0.72
    rex
    -0.65
    wig
    -0.64
    ripp
    -0.63
    Ring
    -0.61
    den
    -0.61
    ike
    -0.59
    att
    -0.59
    xt
    -0.58
    POSITIVE LOGITS
     civilians
    3.41
     civilian
    2.45
     bystanders
    1.74
     combatants
    1.53
     pedestrians
    1.48
     citizens
    1.48
     peasants
    1.43
     villagers
    1.40
     soldiers
    1.39
     Iraqis
    1.38
    Activations Density 0.016%

    No Known Activations