© 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. 21328
    Prev
    Next
    INDEX
    Explanations

    mentions of weapons of mass destruction

    oai_token-act-pair · gpt-3.5-turbo

    references to weapons of mass destruction

    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
     Guest
    -0.79
    akura
    -0.72
     Keys
    -0.66
     Timeline
    -0.63
     Attributes
    -0.62
    stones
    -0.61
    ussions
    -0.61
    sticks
    -0.61
     Signs
    -0.59
    ymes
    -0.59
    POSITIVE LOGITS
     choice
    1.07
     destruction
    1.05
     persuasion
    0.92
    illance
    0.90
     coercion
    0.88
     distraction
    0.87
     oppression
    0.85
     mass
    0.84
     intimidation
    0.82
    choice
    0.81
    Activations Density 0.096%

    No Known Activations