© 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. 6-RES-JB
    11. 11840
    Prev
    Next
    INDEX
    Explanations

    legal terms related to legal actions and inquiries

    oai_token-act-pair · gpt-3.5-turbo

    terms related to legal subpoenas

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    birth
    -0.85
    atomic
    -0.79
    adjust
    -0.75
    ogun
    -0.74
    anguages
    -0.67
    ock
    -0.66
    ocks
    -0.65
    real
    -0.65
    hirt
    -0.65
    opsy
    -0.65
    POSITIVE LOGITS
     subpoen
    1.32
     subpoena
    1.21
     requests
    0.82
    naire
    0.82
     pardon
    0.80
    naires
    0.76
     affidav
    0.76
     compel
    0.75
     summons
    0.75
     probing
    0.74
    Activations Density 0.028%

    No Known Activations