© 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. 24492
    Prev
    Next
    INDEX
    Explanations

    references to violent actions involving shooting

    oai_token-act-pair · gpt-3.5-turbo

    references to shooting incidents and gun violence

    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
    DragonMagazine
    -0.84
    SEA
    -0.81
    coal
    -0.78
    Factor
    -0.77
    Balance
    -0.75
    é¾įå¥ij士
    -0.74
    Maps
    -0.73
    States
    -0.73
    pillar
    -0.73
    Graphics
    -0.69
    POSITIVE LOGITS
     dead
    1.35
     fatally
    0.98
     deceased
    0.92
     wounding
    0.86
     twice
    0.84
     multiple
    0.83
     lifeless
    0.83
     unarmed
    0.82
     gunshot
    0.81
     rampage
    0.81
    Activations Density 0.052%

    No Known Activations