© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 16657
    Prev
    Next
    INDEX
    Explanations

    references to the term "Supreme Court" or words related to legal and judicial matters

    oai_token-act-pair · gpt-3.5-turbo

    variations of the word "supreme" and related terms

    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
    hyde
    -0.74
    sbm
    -0.74
     Nights
    -0.68
     Masquerade
    -0.66
     fingertips
    -0.63
    ttes
    -0.63
    housing
    -0.62
     Sheen
    -0.62
     inacc
    -0.61
     Burnett
    -0.60
    POSITIVE LOGITS
    reme
    1.64
    ersed
    1.25
    rising
    1.20
    olicy
    1.13
    rab
    1.11
    ortun
    1.09
    ra
    1.05
    rem
    1.05
    ension
    1.01
    resso
    0.99
    Activations Density 0.031%

    No Known Activations