© 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. 6-RES-JB
    11. 9415
    Prev
    Next
    INDEX
    Explanations

    phrases related to legal actions or lawsuits

    oai_token-act-pair · gpt-3.5-turbo

    references to legal suits and litigation terminology

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    atal
    -0.82
    combe
    -0.74
    obyl
    -0.73
    peak
    -0.72
    Chart
    -0.71
    ussen
    -0.68
    ode
    -0.66
    erd
    -0.65
    odes
    -0.64
    airo
    -0.62
    POSITIVE LOGITS
     alleging
    1.02
     alleges
    1.01
     filed
    0.98
     against
    0.90
     suing
    0.88
     lawsuit
    0.85
     settlement
    0.82
     Against
    0.82
     AGA
    0.81
     accusing
    0.80
    Activations Density 0.072%

    No Known Activations