© 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. 6-RES-JB
    11. 20744
    Prev
    Next
    INDEX
    Explanations

    legal terms and actions like lawsuits, allegations, and violations

    oai_token-act-pair · gpt-3.5-turbo

    words related to legal allegations and accusations

    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
    OVA
    -0.77
    aver
    -0.73
    obyl
    -0.72
    talk
    -0.71
    aa
    -0.69
    think
    -0.68
    eteria
    -0.68
    ocl
    -0.66
    osc
    -0.65
    patch
    -0.65
    POSITIVE LOGITS
     alleges
    0.97
     alleging
    0.90
     allege
    0.76
     suing
    0.74
     violations
    0.71
     wrongful
    0.70
     accuses
    0.70
     accusing
    0.69
     sue
    0.69
     allegations
    0.69
    Activations Density 0.065%

    No Known Activations