© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 10-RES-JB
    11. 17418
    Prev
    Next
    INDEX
    Explanations

    companies and individuals involved in legal disputes

    oai_token-act-pair · gpt-3.5-turbo

    legal actions involving lawsuits and litigation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Gau
    -0.70
    icators
    -0.69
     ensemble
    -0.68
    oeuv
    -0.67
    é»Ĵ
    -0.66
     Favor
    -0.65
    intosh
    -0.65
     histor
    -0.65
     hobbies
    -0.64
     Assass
    -0.64
    POSITIVE LOGITS
     antitrust
    1.35
     bankruptcy
    1.35
     patents
    1.21
     patent
    1.16
     IPO
    1.14
     shareholder
    1.08
     sued
    1.07
     trademarks
    1.06
     customers
    1.06
     liability
    1.06
    Activations Density 0.528%

    No Known Activations