© 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. 10-RES-JB
    11. 1097
    Prev
    Next
    INDEX
    Explanations

    phrases related to legal terms and perspectives, particularly focusing on specific legal documents, rulings, and viewpoints

    oai_token-act-pair · gpt-3.5-turbo

    references to legal terms and procedures

    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
    needed
    -0.72
    ogie
    -0.68
    avorite
    -0.66
    ortium
    -0.64
     TAMADRA
    -0.62
    regular
    -0.62
    lishes
    -0.60
     unfairly
    -0.58
    owship
    -0.58
    Ore
    -0.58
    POSITIVE LOGITS
     standpoint
    2.06
     perspective
    1.79
     vantage
    1.71
     onwards
    1.61
     viewpoint
    1.51
     onward
    1.39
     perspectives
    1.24
     point
    1.09
     outset
    1.08
     Perspective
    1.07
    Activations Density 0.256%

    No Known Activations