© 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. 11-RES-JB
    11. 5067
    Prev
    Next
    INDEX
    Explanations

    phrases related to legal agreements and actions

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating agreements, commitments, or connections between parties

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     spotting
    -0.82
     STATS
    -0.69
     Fay
    -0.69
     Solitaire
    -0.68
     FANTASY
    -0.65
    ilet
    -0.65
    aroo
    -0.65
     Marks
    -0.65
    697
    -0.63
    Boo
    -0.63
    POSITIVE LOGITS
     belonged
    1.08
     belong
    1.07
     belongs
    1.07
     aspire
    0.96
     owe
    0.94
     entrusted
    0.89
     entitle
    0.89
     subscribe
    0.88
     allegiance
    0.88
     applies
    0.87
    Activations Density 0.061%

    No Known Activations