© 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. 14564
    Prev
    Next
    INDEX
    Explanations

    words related to legal cases or proceedings

    oai_token-act-pair · gpt-3.5-turbo

    the term "case" in various contexts

    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
    ¥ŀ
    -0.87
    è¦ļéĨĴ
    -0.74
    antle
    -0.73
    lished
    -0.69
    æĺ¯
    -0.68
    taboola
    -0.65
     oversized
    -0.65
     arrang
    -0.64
    romeda
    -0.64
     advoc
    -0.63
    POSITIVE LOGITS
    xual
    1.66
    ase
    1.23
    asing
    0.93
    lease
    0.91
    ases
    0.88
    construct
    0.80
    ased
    0.79
    eer
    0.77
    ete
    0.76
    asers
    0.75
    Activations Density 0.010%

    No Known Activations