© 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. 11-RES-JB
    11. 3446
    Prev
    Next
    INDEX
    Explanations

    confrontation or conflict situations involving arguments between individuals

    oai_token-act-pair · gpt-3.5-turbo

    incidents involving arguments or conflicts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ãĥĬ
    -0.81
    2020
    -0.79
    ãĤ½
    -0.73
    Launch
    -0.71
    ãĥķ
    -0.70
    angible
    -0.69
    upload
    -0.67
    ãĥł
    -0.66
    achu
    -0.66
    icon
    -0.66
    POSITIVE LOGITS
     superiors
    1.55
     supervisors
    1.47
     supervisor
    1.45
     boun
    1.31
     dispatcher
    1.28
     guards
    1.26
     manager
    1.25
     managers
    1.25
     administrators
    1.18
     management
    1.14
    Activations Density 0.427%

    No Known Activations