© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 0-RES-JB
    6. 1276
    Prev
    Next
    INDEX
    Explanations

    mentions or occurrences of the word "lease" or related terms

    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 @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Obst
    -0.63
     Yosh
    -0.63
     Jugg
    -0.62
    ppa
    -0.62
     Videos
    -0.61
    imo
    -0.61
     Oz
    -0.60
     Grimm
    -0.60
     Gab
    -0.60
    aos
    -0.59
    POSITIVE LOGITS
     lease
    4.05
     leases
    3.28
     leasing
    2.65
     leased
    2.40
    lease
    2.17
     tenancy
    1.84
     rent
    1.71
     tenant
    1.71
     tenants
    1.46
     landlord
    1.44
    Activations Density 0.008%

    No Known Activations