© 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. 9-RES-JB
    11. 17480
    Prev
    Next
    INDEX
    Explanations

    instances of physical conflict or violence involving projectiles or aggression

    oai_token-act-pair · gpt-3.5-turbo

    instances of violence or aggressive behavior

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ãĤ´ãĥ³
    -0.95
     suffix
    -0.75
    ãĥĩãĤ£
    -0.73
     immortality
    -0.73
     trillions
    -0.71
    ipel
    -0.71
    nesia
    -0.70
    fried
    -0.70
    cham
    -0.70
    Names
    -0.70
    POSITIVE LOGITS
     protestors
    1.27
     pedestrians
    1.27
     protesters
    1.25
     policemen
    1.24
     demonstrators
    1.23
     assailants
    1.23
     cops
    1.22
     officers
    1.21
     passers
    1.20
     attackers
    1.17
    Activations Density 0.428%

    No Known Activations