© 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. 11-RES-JB
    11. 2694
    Prev
    Next
    INDEX
    Explanations

    information related to weaponry and warfare

    oai_token-act-pair · gpt-3.5-turbo

    references to destructive weapons and related actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Integration
    -0.79
     Cosponsors
    -0.75
    Trend
    -0.75
     Investments
    -0.72
    orses
    -0.72
     Improvement
    -0.70
     motivations
    -0.70
     Background
    -0.69
     approvals
    -0.69
     transitional
    -0.68
    POSITIVE LOGITS
     penetrate
    1.37
     deton
    1.33
     pierced
    1.30
     ric
    1.29
     penetrated
    1.26
     detonated
    1.25
     injure
    1.25
     graz
    1.17
     penet
    1.16
     piercing
    1.15
    Activations Density 0.374%

    No Known Activations