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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 8-RES-JB
    11. 1214
    Prev
    Next
    INDEX
    Explanations

    terms related to military actions, such as bombings, attacks, and campaigns

    oai_token-act-pair · gpt-3.5-turbo

    references to military actions and war-related incidents

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    antha
    -0.76
     Lumin
    -0.74
    ournals
    -0.73
     Laure
    -0.72
     Cind
    -0.70
     Beauty
    -0.70
     Happiness
    -0.70
     Certified
    -0.67
    models
    -0.67
    ience
    -0.66
    POSITIVE LOGITS
     retali
    1.36
     indiscrim
    1.34
     assaults
    1.19
     retaliation
    1.19
     bombardment
    1.16
     attacks
    1.13
     provocation
    1.11
     targeting
    1.11
     escalation
    1.10
     bombings
    1.10
    Activations Density 0.898%

    No Known Activations