© 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. 4-RES-JB
    11. 4743
    Prev
    Next
    INDEX
    Explanations

    phrases related to legal agreements or contracts

    oai_token-act-pair · gpt-3.5-turbo

    terms related to leases and leasing agreements

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

    No Comments

    Negative Logits
    reme
    -0.86
    hematic
    -0.78
    ulhu
    -0.76
     Flavoring
    -0.75
    acco
    -0.75
    oche
    -0.75
    aos
    -0.74
    govtrack
    -0.72
     Unch
    -0.72
    ahi
    -0.72
    POSITIVE LOGITS
    hold
    1.10
    holder
    1.06
     leases
    1.05
    holders
    1.04
     lease
    1.00
     leasing
    0.87
     leased
    0.84
     agreements
    0.82
    heed
    0.82
     upgr
    0.80
    Activations Density 0.006%

    No Known Activations