© 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. 1-RES-JB
    11. 3475
    Prev
    Next
    INDEX
    Explanations

    mentions of or references to shooters, specifically in the context of sports or gaming

    oai_token-act-pair · gpt-3.5-turbo

    references to individuals involved in shooting incidents

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ŃĶ
    -0.77
    arb
    -0.75
    ç«
    -0.70
    notations
    -0.70
    graded
    -0.69
    urn
    -0.69
    undai
    -0.68
    éĥ
    -0.64
    luaj
    -0.63
    cess
    -0.63
    POSITIVE LOGITS
     shooter
    1.42
     shooters
    1.33
     Shooter
    1.26
     snipers
    0.90
    Maker
    0.89
     shooting
    0.85
     gunman
    0.83
     sniper
    0.82
    renheit
    0.81
     Shoot
    0.81
    Activations Density 0.005%

    No Known Activations