© 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. 0-RES-JB
    11. 11354
    Prev
    Next
    INDEX
    Explanations

    lawsuits or legal actions

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of legal actions involving lawsuits

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     routine
    -0.66
    gob
    -0.65
     prec
    -0.63
    cons
    -0.63
     Dalton
    -0.61
    åº
    -0.61
    elf
    -0.59
     Num
    -0.59
     Dynam
    -0.59
    ots
    -0.57
    POSITIVE LOGITS
     sued
    4.06
     suing
    2.43
     sue
    2.40
     lawsuits
    1.64
     lawsuit
    1.52
     filed
    1.37
     lawy
    1.36
     plaintiff
    1.36
     prosecuted
    1.31
     plaintiffs
    1.31
    Activations Density 0.016%

    No Known Activations