© 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. 10-RES-JB
    11. 10622
    Prev
    Next
    INDEX
    Explanations

    information related to violent incidents involving individuals being harmed or killed by others

    oai_token-act-pair · gpt-3.5-turbo

    mentions of violent incidents or fatalities involving individuals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ournals
    -0.87
    thood
    -0.85
    soDeliveryDate
    -0.80
     accomplishments
    -0.76
     scholarships
    -0.76
    Planet
    -0.75
    eworld
    -0.74
    Books
    -0.74
    ospels
    -0.73
    peak
    -0.72
    POSITIVE LOGITS
     assailants
    1.28
     gunfire
    1.16
     thugs
    1.16
     assailant
    1.15
     gunman
    1.13
     gunmen
    1.12
     attackers
    1.12
    andals
    1.08
     intruder
    1.07
     mob
    1.02
    Activations Density 0.367%

    No Known Activations