© 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. 3-RES-JB
    11. 13646
    Prev
    Next
    INDEX
    Explanations

    phrases related to leasing agreements

    oai_token-act-pair · gpt-3.5-turbo

    terms related to leasing agreements and contracts

    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
    reme
    -0.85
    hematic
    -0.74
     Flavoring
    -0.73
    ulhu
    -0.73
     Schwarz
    -0.73
    airo
    -0.71
    ombies
    -0.69
    omsky
    -0.69
    govtrack
    -0.69
    alse
    -0.67
    POSITIVE LOGITS
    hold
    1.16
     leases
    1.11
    holder
    1.11
     lease
    1.08
    holders
    1.02
    heed
    0.94
     leasing
    0.94
     leased
    0.93
     rentals
    0.82
     renewal
    0.79
    Activations Density 0.013%

    No Known Activations