© 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. 3527
    Prev
    Next
    INDEX
    Explanations

    mentions of legal courts

    oai_token-act-pair · gpt-3.5-turbo

    references to judicial or legal proceedings

    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
     livest
    -0.74
     prime
    -0.71
     americ
    -0.65
    ku
    -0.65
    uilt
    -0.63
     epoch
    -0.62
     hol
    -0.61
    akeru
    -0.60
     destro
    -0.60
    dyl
    -0.60
    POSITIVE LOGITS
    auld
    1.08
     Court
    1.03
    Court
    0.95
    court
    0.90
    wright
    0.89
    yer
    0.83
    room
    0.82
     Reporter
    0.80
    yers
    0.78
    rooms
    0.78
    Activations Density 0.013%

    No Known Activations