© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 23661
    Prev
    Next
    INDEX
    Explanations

    terms related to traumatic events or disasters

    oai_token-act-pair · gpt-3.5-turbo

    words associated with historical and social issues, particularly those related to trauma and victimization

    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
    etheless
    -0.80
    ij
    -0.79
    gemony
    -0.77
    ŃĶ
    -0.75
    ynthesis
    -0.72
    thora
    -0.70
    endon
    -0.70
    hran
    -0.70
     Tanz
    -0.68
    stanbul
    -0.68
    POSITIVE LOGITS
     prevention
    1.63
     Prevention
    1.36
     mitigation
    1.27
     victims
    1.10
     detection
    1.09
     survivor
    1.08
     awareness
    1.03
     Awareness
    1.02
     investigations
    1.01
     avoidance
    1.00
    Activations Density 0.463%

    No Known Activations