© 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. 6728
    Prev
    Next
    INDEX
    Explanations

    legal terms or mentions of attorneys in news articles

    oai_token-act-pair · gpt-3.5-turbo

    references to legal professionals and their roles

    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
     obsolete
    -0.66
    STEM
    -0.66
    Quantity
    -0.62
     destined
    -0.61
     trillions
    -0.61
     Directive
    -0.60
    ankind
    -0.60
     foreigner
    -0.59
    Enh
    -0.57
     localization
    -0.56
    POSITIVE LOGITS
     appealed
    1.12
     thanked
    1.09
     alleges
    1.07
     contends
    1.05
     attorney
    1.03
     declined
    1.01
     denies
    1.01
     insists
    0.98
     lawyer
    0.98
     told
    0.96
    Activations Density 0.140%

    No Known Activations