© 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. 3-RES-JB
    11. 21159
    Prev
    Next
    INDEX
    Explanations

    legal terminology or references to courts and their decisions

    oai_token-act-pair · gpt-3.5-turbo

    references to the court system and judicial decisions

    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
     livest
    -0.72
    jiang
    -0.71
     plent
    -0.69
     Motorsport
    -0.68
     Nato
    -0.68
    ktop
    -0.67
     Tao
    -0.66
     Marketable
    -0.64
     Pyro
    -0.64
     ana
    -0.63
    POSITIVE LOGITS
    rooms
    1.06
    room
    0.98
     justices
    0.91
    wright
    0.87
    Court
    0.81
    iffs
    0.80
    court
    0.80
    yer
    0.76
    NEY
    0.74
    yers
    0.74
    Activations Density 0.026%

    No Known Activations