© 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. 1-RES-JB
    11. 10353
    Prev
    Next
    INDEX
    Explanations

    words related to legal proceedings and courtroom activities

    oai_token-act-pair · gpt-3.5-turbo

    terms related to legal proceedings and litigation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    erd
    -0.94
    eele
    -0.84
    bern
    -0.80
    atomic
    -0.76
    ODE
    -0.75
    olls
    -0.71
    odes
    -0.70
    ordinate
    -0.69
    bies
    -0.68
    apo
    -0.67
    POSITIVE LOGITS
     litigation
    1.13
     challeng
    0.90
    suits
    0.82
     proceedings
    0.82
    emate
    0.78
     warr
    0.75
     filings
    0.71
     disputes
    0.71
     settlement
    0.70
    ĸļ
    0.70
    Activations Density 0.008%

    No Known Activations