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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 4-RES-JB
    11. 12412
    Prev
    Next
    INDEX
    Explanations

    words related to explosions and violent incidents

    oai_token-act-pair · gpt-3.5-turbo

    references to violent incidents, explosions, and their consequences

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

    No Comments

    Negative Logits
    channelAvailability
    -0.79
    utical
    -0.78
     Virtue
    -0.70
    Intern
    -0.69
    Balt
    -0.68
     Protoss
    -0.66
    é¾įå
    -0.66
    isSpecialOrderable
    -0.65
     Gins
    -0.65
     virtues
    -0.65
    POSITIVE LOGITS
     spree
    1.06
     rampage
    0.84
    EMS
    0.83
     victims
    0.79
     deton
    0.78
     victim
    0.78
     bombing
    0.77
     detonated
    0.77
     perpetrated
    0.76
     explosion
    0.76
    Activations Density 0.316%

    No Known Activations