© 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. 3-RES-JB
    11. 2788
    Prev
    Next
    INDEX
    Explanations

    legal terms related to court cases and defendants

    oai_token-act-pair · gpt-3.5-turbo

    references to defendants in a legal context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ories
    -0.82
    olen
    -0.78
    ür
    -0.76
    efully
    -0.68
    yip
    -0.68
    ikarp
    -0.68
    drive
    -0.67
    ģ«
    -0.67
    eful
    -0.67
    lighting
    -0.66
    POSITIVE LOGITS
     defendant
    0.87
     defendants
    0.86
     pled
    0.84
     Defendant
    0.83
     plead
    0.74
     convicted
    0.74
     accused
    0.74
     sentenced
    0.72
     Defendants
    0.72
    eering
    0.71
    Activations Density 0.012%

    No Known Activations