© 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. 2-RES-JB
    11. 5486
    Prev
    Next
    INDEX
    Explanations

    phrases related to legal actions

    oai_token-act-pair · gpt-3.5-turbo

    instances of legal actions or lawsuits

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    oyal
    -0.70
    agents
    -0.70
    apo
    -0.69
    existent
    -0.67
    ollower
    -0.67
    ordinate
    -0.67
    population
    -0.66
    rentices
    -0.66
    ococ
    -0.65
    atomic
    -0.65
    POSITIVE LOGITS
     sued
    0.98
     sue
    0.97
     suing
    0.94
    suits
    0.91
    rays
    0.86
    hiro
    0.83
    suit
    0.82
    ulence
    0.81
     against
    0.78
     challeng
    0.77
    Activations Density 0.012%

    No Known Activations