© 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. 3392
    Prev
    Next
    INDEX
    Explanations

    mentions of hostility or hostile behavior in the text

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "hostile" or related phrases

    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
    oled
    -0.87
    orah
    -0.86
    ucket
    -0.83
    20439
    -0.81
    akings
    -0.80
    arist
    -0.79
    alt
    -0.75
    attr
    -0.74
    issue
    -0.74
    acea
    -0.74
    POSITIVE LOGITS
     hostile
    1.32
     takeover
    1.01
     undermin
    0.94
     hostility
    0.94
     citiz
    0.83
     invaders
    0.83
     invasion
    0.81
     retaliation
    0.81
     interference
    0.78
     friendly
    0.77
    Activations Density 0.011%

    No Known Activations